336 KiB
336 KiB
Лабораторная работа 6¶
Крестики-нолики https://github.com/nczempin/gym-tic-tac-toe/tree/master
Перевод среды на Gymnasium¶
In [1]:
import gymnasium as gym
from gymnasium import spaces
class TicTacToeEnv(gym.Env):
metadata = {'render.modes': ['human']}
symbols = ['O', ' ', 'X']
def __init__(self):
super().__init__()
self.action_space = spaces.Discrete(9)
self.observation_space = spaces.Discrete(9 * 3 * 2)
self.reset()
def step(self, action):
done = False
reward = 0
p, square = action
board = self.state['board']
proposed = board[square]
om = self.state['on_move']
if proposed != 0:
print(f"Незаконный ход: Клетка {square} занята.")
done = True
reward = -1 * om
if p != om:
print(f"Незаконный ход: игрок {p} не ходит")
done = True
reward = -1 * om
else:
board[square] = p
self.state['on_move'] = -p
for i in range(3):
if (board[i * 3] == p and board[i * 3 + 1] == p and board[i * 3 + 2] == p) or \
(board[i] == p and board[i + 3] == p and board[i + 6] == p):
reward = p
done = True
break
if (board[0] == p and board[4] == p and board[8] == p) or \
(board[2] == p and board[4] == p and board[6] == p):
reward = p
done = True
return self.state, reward, done, {}
def reset(self):
self.state = {}
self.state['board'] = [0, 0, 0, 0, 0, 0, 0, 0, 0]
self.state['on_move'] = 1
return self.state, {}
def render(self, close=False):
if close:
return
print("on move: " , self.symbols[self.state['on_move']+1])
for i in range (9):
print (self.symbols[self.state['board'][i]+1], end=" ");
if ((i % 3) == 2):
print();
def move_generator(self):
moves = []
for i in range(9):
if self.state['board'][i] == 0:
p = self.state['on_move']
m = [p, i]
moves.append(m)
return moves
Реализация агента¶
In [2]:
import random
class RandomTicTacToeAgent:
def __init__(self, symbol):
self.symbol = symbol
def get_action(self, moves):
return random.choice(moves)
Основной цикл обучения¶
In [3]:
env = TicTacToeEnv()
agent = RandomTicTacToeAgent(symbol=1)
num_episodes = 500
collected_rewards = []
oom = 1
for i in range(num_episodes):
state, _ = env.reset()
total_reward = 0
done = False
om = oom
for j in range(9):
moves = env.move_generator()
if not moves:
break
if len(moves) == 1:
move = moves[0]
else:
move = agent.get_action(moves)
next_state, reward, done, info = env.step(move)
total_reward += reward
state = next_state
env.render()
if done:
break
om = -om
collected_rewards.append(total_reward)
print(f"Episode {i+1}, Total Reward: {total_reward}")
average_reward = sum(collected_rewards) / len(collected_rewards)
print(f"Average Reward: {average_reward}")
on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X on move: X O O X O X O X X Episode 1, Total Reward: -1 Average Reward: -1.0 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O X O on move: O X X X O O X O on move: X X X O X O O X O Episode 2, Total Reward: -1 Average Reward: -1.0 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O X O on move: O X X X O O X O Episode 3, Total Reward: 1 Average Reward: -0.3333333333333333 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O O X X X X Episode 4, Total Reward: 1 Average Reward: 0.0 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X Episode 5, Total Reward: -1 Average Reward: -0.2 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X O X on move: X O X O X O X Episode 6, Total Reward: -1 Average Reward: -0.3333333333333333 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O Episode 7, Total Reward: -1 Average Reward: -0.42857142857142855 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O X X O on move: O X O O X X X O on move: X X O O X O X X O Episode 8, Total Reward: -1 Average Reward: -0.5 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X O O X O X on move: X X X O O X O O X on move: O X X X O O X O O X Episode 9, Total Reward: 1 Average Reward: -0.3333333333333333 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X on move: X X O O O O X X X on move: O X O O O O X X X X Episode 10, Total Reward: 1 Average Reward: -0.2 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X X O O X on move: X O X X X O O O X on move: O O X X X X O O O X Episode 11, Total Reward: 0 Average Reward: -0.18181818181818182 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O O O X on move: X X X X O O O O X on move: O X X X X O O O O X Episode 12, Total Reward: 1 Average Reward: -0.08333333333333333 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X O X X on move: O X O O X O X X on move: X X O O O X O X X on move: O X O O O X O X X X Episode 13, Total Reward: 1 Average Reward: 0.0 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O O X X X O on move: O O O X X X X O on move: X O O X X X O X O on move: O O O X X X X O X O Episode 14, Total Reward: 1 Average Reward: 0.07142857142857142 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X O X O on move: X O O X X X O X O on move: O O O X X X X O X O Episode 15, Total Reward: 1 Average Reward: 0.13333333333333333 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X X O O X O X on move: O X O O X O X X Episode 16, Total Reward: 1 Average Reward: 0.1875 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X O X on move: X O X X O X O on move: O O X X X O X O on move: X O X X X O O X O on move: O O X X X O O X O X Episode 17, Total Reward: 0 Average Reward: 0.17647058823529413 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X O O X on move: X O X X X O O O X on move: O O X X X O O O X X Episode 18, Total Reward: 0 Average Reward: 0.16666666666666666 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O Episode 19, Total Reward: 1 Average Reward: 0.21052631578947367 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X X O O on move: X O X X O X X O O Episode 20, Total Reward: -1 Average Reward: 0.15 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X O X X O on move: O X O X O X X O on move: X X O X O O X X O on move: O X O X O O X X X O Episode 21, Total Reward: 0 Average Reward: 0.14285714285714285 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X O X O O on move: O X X O X O O X on move: X O X X O X O O X on move: O O X X X O X O O X Episode 22, Total Reward: 1 Average Reward: 0.18181818181818182 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X X O O X O X on move: O X X O O X O X on move: X X X O O O X O X on move: O X X O O O X X O X Episode 23, Total Reward: 0 Average Reward: 0.17391304347826086 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O O X on move: O X X O X O O X on move: X X X O O X O O X Episode 24, Total Reward: -1 Average Reward: 0.125 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O X O O X on move: X X X O X O O O X on move: O X X X O X O O O X Episode 25, Total Reward: 1 Average Reward: 0.16 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X Episode 26, Total Reward: 1 Average Reward: 0.19230769230769232 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 27, Total Reward: -1 Average Reward: 0.14814814814814814 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O X O X X X O O on move: X X O X X X O O O on move: O X O X X X O O O X Episode 28, Total Reward: 1 Average Reward: 0.17857142857142858 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O X X O on move: O O X O X X X O on move: X O X O O X X X O on move: O X O X O O X X X O Episode 29, Total Reward: 0 Average Reward: 0.1724137931034483 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X O X X O O X on move: O O X X O X O X on move: X O O X X O X O X on move: O O X O X X O X O X Episode 30, Total Reward: 0 Average Reward: 0.16666666666666666 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O X O X on move: O O X O X X O X Episode 31, Total Reward: 1 Average Reward: 0.1935483870967742 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X O X O O on move: O X X X O X O O on move: X O X X X O X O O Episode 32, Total Reward: -1 Average Reward: 0.15625 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X O X O O X on move: O X O X X O O X on move: X X O X X O O O X on move: O X X O X X O O O X Episode 33, Total Reward: 1 Average Reward: 0.18181818181818182 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X O X O on move: O X O X X O X O on move: X X O X X O O X O on move: O X O X X X O O X O Episode 34, Total Reward: 0 Average Reward: 0.17647058823529413 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O O X O X on move: O X O O X X O X Episode 35, Total Reward: 1 Average Reward: 0.2 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O O X O on move: X X X X O O O X O on move: O X X X X O O O X O Episode 36, Total Reward: 1 Average Reward: 0.2222222222222222 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X Episode 37, Total Reward: 1 Average Reward: 0.24324324324324326 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X O X O O X on move: O X O X O O X X on move: X X O X O O O X X on move: O X O X O O X O X X Episode 38, Total Reward: 1 Average Reward: 0.2631578947368421 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X O X O X O X on move: O O X X O X O X on move: X O X X O O X O X on move: O O X X X O O X O X Episode 39, Total Reward: 0 Average Reward: 0.2564102564102564 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O X O X X O on move: X X O X X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 40, Total Reward: -1 Average Reward: 0.225 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X O X O O X on move: O X O X O O X X on move: X O X O X O O X X on move: O O X O X O O X X X Episode 41, Total Reward: 1 Average Reward: 0.24390243902439024 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O O X X X X on move: X O O O O X X X X Episode 42, Total Reward: -1 Average Reward: 0.21428571428571427 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O X X O on move: O X O O X X X O on move: X X O O X X X O O on move: O X O O X X X X O O Episode 43, Total Reward: 1 Average Reward: 0.23255813953488372 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O X O X Episode 44, Total Reward: 1 Average Reward: 0.25 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X X O O O X on move: X X X O X O O O X Episode 45, Total Reward: -1 Average Reward: 0.2222222222222222 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X O X O O X X on move: O X O X O O X X on move: X X O X O O O X X Episode 46, Total Reward: -1 Average Reward: 0.1956521739130435 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X X O O X O X on move: O X O X O X O X on move: X X O X O X O O X Episode 47, Total Reward: -1 Average Reward: 0.1702127659574468 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O X O O X X X Episode 48, Total Reward: 1 Average Reward: 0.1875 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X Episode 49, Total Reward: -1 Average Reward: 0.16326530612244897 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X O X X O X O on move: O X O X X O X O on move: X X O O X X O X O on move: O X O X O X X O X O Episode 50, Total Reward: 0 Average Reward: 0.16 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X O X X O Episode 51, Total Reward: -1 Average Reward: 0.13725490196078433 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X O X X O O X on move: O O X X O X O X on move: X O X X O X O O X on move: O O X X X O X O O X Episode 52, Total Reward: 1 Average Reward: 0.15384615384615385 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O O X X O on move: O X O O X X X O on move: X X O O X O X X O on move: O X O X O X O X X O Episode 53, Total Reward: 1 Average Reward: 0.16981132075471697 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O O X O X X O X on move: X O X O O X X O X on move: O O X O X O X X O X Episode 54, Total Reward: 0 Average Reward: 0.16666666666666666 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X O X O O X Episode 55, Total Reward: 1 Average Reward: 0.18181818181818182 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X O X O X on move: X O X X O X O X O Episode 56, Total Reward: -1 Average Reward: 0.16071428571428573 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O X O O X Episode 57, Total Reward: 1 Average Reward: 0.17543859649122806 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O X O X O X Episode 58, Total Reward: 1 Average Reward: 0.1896551724137931 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O Episode 59, Total Reward: -1 Average Reward: 0.1694915254237288 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X O X O O X on move: O X O X O O X X on move: X O X O X O O X X on move: O O X O X O O X X X Episode 60, Total Reward: 1 Average Reward: 0.18333333333333332 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X on move: X X O O O O X X X on move: O X O O O O X X X X Episode 61, Total Reward: 1 Average Reward: 0.19672131147540983 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X O X O on move: O X X O X O X O on move: X X X O X O X O O Episode 62, Total Reward: -1 Average Reward: 0.1774193548387097 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O X O X X O on move: X O X O X X O on move: O O X O X X O X on move: X O X O X X O O X on move: O O X O X X X O O X Episode 63, Total Reward: 1 Average Reward: 0.19047619047619047 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O X O X O X on move: X X O O X O X on move: O X O O X X O X on move: X X O O X X O O X on move: O X O O X X O O X X Episode 64, Total Reward: 1 Average Reward: 0.203125 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X Episode 65, Total Reward: -1 Average Reward: 0.18461538461538463 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X X O O Episode 66, Total Reward: 1 Average Reward: 0.19696969696969696 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O X O X X X Episode 67, Total Reward: 1 Average Reward: 0.208955223880597 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 68, Total Reward: -1 Average Reward: 0.19117647058823528 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O X O X O X Episode 69, Total Reward: 1 Average Reward: 0.2028985507246377 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O X X O on move: O X X O O X X O on move: X X X O O X X O O on move: O X X X O O X X O O Episode 70, Total Reward: 1 Average Reward: 0.21428571428571427 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X Episode 71, Total Reward: 1 Average Reward: 0.22535211267605634 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O X X O on move: O X O O X X X O on move: X X O O O X X X O on move: O X O O O X X X X O Episode 72, Total Reward: 0 Average Reward: 0.2222222222222222 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O X O on move: O X X O X O X O on move: X X X O O X O X O on move: O X X O O X O X O X Episode 73, Total Reward: 1 Average Reward: 0.2328767123287671 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X X O X X O O on move: X O X X O X X O O Episode 74, Total Reward: -1 Average Reward: 0.21621621621621623 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X Episode 75, Total Reward: -1 Average Reward: 0.2 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X X O on move: O O O X X X X O on move: X O O O X X X X O on move: O X O O O X X X X O Episode 76, Total Reward: 0 Average Reward: 0.19736842105263158 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X O X O O X X on move: O O X O O X X X Episode 77, Total Reward: 1 Average Reward: 0.2077922077922078 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X O O X X O on move: X X O X O O X X O on move: O X O X X O O X X O Episode 78, Total Reward: 1 Average Reward: 0.21794871794871795 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X on move: X X O O O X X X O on move: O X X O O O X X X O Episode 79, Total Reward: 0 Average Reward: 0.21518987341772153 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O X O X on move: O X X O O X O X on move: X X O X O O X O X on move: O X X O X O O X O X Episode 80, Total Reward: 1 Average Reward: 0.225 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O Episode 81, Total Reward: 1 Average Reward: 0.2345679012345679 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O X O X X X O O on move: X X O X X X O O O on move: O X O X X X O O X O Episode 82, Total Reward: 0 Average Reward: 0.23170731707317074 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X Episode 83, Total Reward: 1 Average Reward: 0.24096385542168675 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X O X X O O on move: X X X O O X X O O on move: O X X O O X X O X O Episode 84, Total Reward: 1 Average Reward: 0.25 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X O X O O on move: O X X O X O O X Episode 85, Total Reward: 1 Average Reward: 0.25882352941176473 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O X O O X on move: X X X O O X O O X on move: O X X X O O X O O X Episode 86, Total Reward: 1 Average Reward: 0.26744186046511625 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O Episode 87, Total Reward: 1 Average Reward: 0.27586206896551724 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O O X on move: O X O X X O O X on move: X O X O X X O O X on move: O O X O X X X O O X Episode 88, Total Reward: 1 Average Reward: 0.2840909090909091 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X O X O O X X on move: O O X X O O X X on move: X O X X O O O X X on move: O X O X X O O O X X Episode 89, Total Reward: 0 Average Reward: 0.2808988764044944 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O O X O X Episode 90, Total Reward: -1 Average Reward: 0.26666666666666666 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O Episode 91, Total Reward: 1 Average Reward: 0.27472527472527475 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X O O X X on move: X O X X O O O X X on move: O X O X X O O O X X Episode 92, Total Reward: 0 Average Reward: 0.2717391304347826 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X O X on move: X O X X O O X on move: O O X X O O X X on move: X O X X O O O X X on move: O O X X X O O O X X Episode 93, Total Reward: 0 Average Reward: 0.26881720430107525 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X on move: O X X O O O X X on move: X X X O O O O X X Episode 94, Total Reward: -1 Average Reward: 0.2553191489361702 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X O X X O X O on move: X X O O X X O X O on move: O X O X O X X O X O Episode 95, Total Reward: 0 Average Reward: 0.25263157894736843 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O O X on move: O X O X O O X X Episode 96, Total Reward: 1 Average Reward: 0.2604166666666667 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X X O O on move: X O X O X X X O O on move: O O X O X X X X O O Episode 97, Total Reward: 1 Average Reward: 0.26804123711340205 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O O X X X O on move: O O O X X X X O Episode 98, Total Reward: 1 Average Reward: 0.2755102040816326 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O X O X X X O O on move: X X O X X X O O O on move: O X O X X X O X O O Episode 99, Total Reward: 1 Average Reward: 0.2828282828282828 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O on move: X X X X X O O O O Episode 100, Total Reward: -1 Average Reward: 0.27 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O X O X O X Episode 101, Total Reward: 1 Average Reward: 0.27722772277227725 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O O X X X X on move: X O O O X X O X X Episode 102, Total Reward: -1 Average Reward: 0.2647058823529412 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X O O X X O on move: X O X X O O X X O Episode 103, Total Reward: -1 Average Reward: 0.2524271844660194 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X O X O O on move: O X X X O X O O Episode 104, Total Reward: 1 Average Reward: 0.25961538461538464 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O Episode 105, Total Reward: -1 Average Reward: 0.24761904761904763 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O X O X X O on move: X X O X O X O on move: O X O X O X X O Episode 106, Total Reward: 1 Average Reward: 0.25471698113207547 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X on move: O X X X O O O X on move: X O X X X O O O X on move: O O X X X X O O O X Episode 107, Total Reward: 0 Average Reward: 0.2523364485981308 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O Episode 108, Total Reward: 1 Average Reward: 0.25925925925925924 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O Episode 109, Total Reward: 1 Average Reward: 0.26605504587155965 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O X O X on move: O X O O X X O X on move: X X O O X X O X O on move: O X O O X X X O X O Episode 110, Total Reward: 1 Average Reward: 0.2727272727272727 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O X O O on move: X O X X X O X O O on move: O O X X X X O X O O Episode 111, Total Reward: 1 Average Reward: 0.27927927927927926 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X O X O O X X on move: O O X O O X X X Episode 112, Total Reward: 1 Average Reward: 0.2857142857142857 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O O X O on move: X X X X O O O X O on move: O X X X X O O O X O Episode 113, Total Reward: 1 Average Reward: 0.2920353982300885 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O X O X X O Episode 114, Total Reward: 1 Average Reward: 0.2982456140350877 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X O X O X O on move: O X O X O X X O Episode 115, Total Reward: 1 Average Reward: 0.30434782608695654 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X O X X X O O Episode 116, Total Reward: 1 Average Reward: 0.3103448275862069 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O O X X O on move: O X O O X X O X on move: X X O O O X X O X on move: O X X O O O X X O X Episode 117, Total Reward: 0 Average Reward: 0.3076923076923077 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O X O on move: O X X O O X X O on move: X X X O O O X X O on move: O X X O O O X X X O Episode 118, Total Reward: 0 Average Reward: 0.3050847457627119 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X X O O X O X on move: O X O O X X O X on move: X X O O O X X O X Episode 119, Total Reward: -1 Average Reward: 0.29411764705882354 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X X O O X O X Episode 120, Total Reward: -1 Average Reward: 0.2833333333333333 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X on move: X O O O X X X O X Episode 121, Total Reward: -1 Average Reward: 0.2727272727272727 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X O X X X O O Episode 122, Total Reward: 1 Average Reward: 0.2786885245901639 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O O X on move: O X X O X O O X Episode 123, Total Reward: 1 Average Reward: 0.2845528455284553 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X O O X X on move: X O X X O O O X X on move: O X O X X O O O X X Episode 124, Total Reward: 0 Average Reward: 0.28225806451612906 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O X X O on move: O X X O O X X O on move: X X X O O O X X O on move: O X X O O O X X O X Episode 125, Total Reward: 0 Average Reward: 0.28 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O O X X X O on move: O X O O X X X O on move: X X O O X X O X O on move: O X O O X X X O X O Episode 126, Total Reward: 1 Average Reward: 0.2857142857142857 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O X O O X X on move: X X O O X O O X X on move: O X O O X X O O X X Episode 127, Total Reward: 1 Average Reward: 0.29133858267716534 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O O X X O on move: O X O O X X X O on move: X O X O O X X X O Episode 128, Total Reward: -1 Average Reward: 0.28125 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O X O O X X Episode 129, Total Reward: 1 Average Reward: 0.2868217054263566 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X O X O X on move: O X O X O X O X on move: X X O X O O X O X on move: O X O X O O X O X X Episode 130, Total Reward: 1 Average Reward: 0.2923076923076923 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O X O O O X X X on move: X X O O O O X X X on move: O X O O O O X X X X Episode 131, Total Reward: 1 Average Reward: 0.29770992366412213 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O X X O Episode 132, Total Reward: -1 Average Reward: 0.2878787878787879 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O X O on move: O X O X O X X O Episode 133, Total Reward: 1 Average Reward: 0.2932330827067669 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X X O on move: O O O X X X X O on move: X O O O X X X X O on move: O O O X O X X X X O Episode 134, Total Reward: 1 Average Reward: 0.29850746268656714 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O X O X X X O O on move: X X O X X O X O O Episode 135, Total Reward: -1 Average Reward: 0.28888888888888886 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O O X X X O on move: O O O X X X X O on move: X O O X X O X X O Episode 136, Total Reward: -1 Average Reward: 0.27941176470588236 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X X O X O O X on move: O X O X O O X X Episode 137, Total Reward: 1 Average Reward: 0.2846715328467153 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O Episode 138, Total Reward: 1 Average Reward: 0.2898550724637681 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X O X X O X O on move: O O X X X O X O Episode 139, Total Reward: 1 Average Reward: 0.2949640287769784 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X Episode 140, Total Reward: 1 Average Reward: 0.3 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O X O X O X on move: X X O O X O X on move: O X O O X X O X on move: X X O O O X X O X on move: O X O O O X X X O X Episode 141, Total Reward: 1 Average Reward: 0.3049645390070922 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X on move: X O O X X X O O X on move: O O O X X X X O O X Episode 142, Total Reward: 1 Average Reward: 0.30985915492957744 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X O X on move: X O X X O O X on move: O O X X O X O X on move: X O X X O X O X O Episode 143, Total Reward: -1 Average Reward: 0.3006993006993007 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X X O O Episode 144, Total Reward: 1 Average Reward: 0.3055555555555556 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X O X O X X O on move: O O X O X X X O on move: X O X O O X X X O on move: O O X O O X X X X O Episode 145, Total Reward: 1 Average Reward: 0.3103448275862069 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O Episode 146, Total Reward: 1 Average Reward: 0.3150684931506849 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X X O X O O on move: X X X X O X O O O Episode 147, Total Reward: -1 Average Reward: 0.30612244897959184 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O X O O X O X X Episode 148, Total Reward: 1 Average Reward: 0.3108108108108108 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O X O X Episode 149, Total Reward: -1 Average Reward: 0.30201342281879195 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X X O O X O Episode 150, Total Reward: 1 Average Reward: 0.30666666666666664 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X O O X X O on move: X X X O O X X O O on move: O X X X O O X X O O Episode 151, Total Reward: 1 Average Reward: 0.31125827814569534 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O O X O X on move: O X O X O X O X on move: X O X O X O X O X on move: O O X X O X O X O X Episode 152, Total Reward: 1 Average Reward: 0.3157894736842105 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X O X O Episode 153, Total Reward: -1 Average Reward: 0.30718954248366015 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O Episode 154, Total Reward: 1 Average Reward: 0.3116883116883117 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O X O on move: O O X X O X O X Episode 155, Total Reward: 1 Average Reward: 0.3161290322580645 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O O O X X on move: X X X O O O X X O on move: O X X O O O X X O X Episode 156, Total Reward: 0 Average Reward: 0.3141025641025641 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X Episode 157, Total Reward: -1 Average Reward: 0.3057324840764331 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X O X O on move: O X O X X O X O on move: X X O O X X O X O on move: O X X O O X X O X O Episode 158, Total Reward: 1 Average Reward: 0.310126582278481 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O O X X O on move: O X O O X X X O on move: X X O O X X O X O on move: O X X O O X X O X O Episode 159, Total Reward: 1 Average Reward: 0.31446540880503143 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X O X O X O on move: O X O X O X X O on move: X X O X O O X X O on move: O X O X O X O X X O Episode 160, Total Reward: 1 Average Reward: 0.31875 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X X O X O O Episode 161, Total Reward: 1 Average Reward: 0.32298136645962733 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O X O X O on move: O X O X X O X O Episode 162, Total Reward: 1 Average Reward: 0.3271604938271605 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O X O X X O on move: X X O X O X O on move: O X O X O X X O Episode 163, Total Reward: 1 Average Reward: 0.3312883435582822 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O O O X X on move: X X X O O O O X X Episode 164, Total Reward: -1 Average Reward: 0.3231707317073171 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O X O X O X on move: X X O X O O X Episode 165, Total Reward: -1 Average Reward: 0.3151515151515151 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X on move: X O O O X O X X X Episode 166, Total Reward: -1 Average Reward: 0.3072289156626506 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O Episode 167, Total Reward: 1 Average Reward: 0.31137724550898205 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X X O X X on move: X O O O X X O X X on move: O X O O O X X O X X Episode 168, Total Reward: 1 Average Reward: 0.31547619047619047 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X Episode 169, Total Reward: 1 Average Reward: 0.31952662721893493 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O Episode 170, Total Reward: -1 Average Reward: 0.31176470588235294 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O X O on move: O X X X O O X O Episode 171, Total Reward: 1 Average Reward: 0.3157894736842105 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O X O X Episode 172, Total Reward: 1 Average Reward: 0.31976744186046513 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O X O O Episode 173, Total Reward: 1 Average Reward: 0.3236994219653179 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O X O on move: O X X X O O X O Episode 174, Total Reward: 1 Average Reward: 0.3275862068965517 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O X O X on move: O X X O O X O X Episode 175, Total Reward: 1 Average Reward: 0.3314285714285714 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O X O X X O X on move: X O X O X X O O X on move: O O X O X X X O O X Episode 176, Total Reward: 1 Average Reward: 0.3352272727272727 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O O O X on move: X O X X X O O O X on move: O O X X X X O O O X Episode 177, Total Reward: 0 Average Reward: 0.3333333333333333 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X on move: X O O X O X X O X Episode 178, Total Reward: -1 Average Reward: 0.3258426966292135 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O X O on move: O O X X X O X O Episode 179, Total Reward: 1 Average Reward: 0.329608938547486 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O X O on move: O O X X X O X O on move: X O X X O X O X O on move: O X O X X O X O X O Episode 180, Total Reward: 0 Average Reward: 0.3277777777777778 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O on move: X X X O X X O O O Episode 181, Total Reward: -1 Average Reward: 0.32044198895027626 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X O O X X O on move: X X X O O X X O O on move: O X X X O O X X O O Episode 182, Total Reward: 1 Average Reward: 0.3241758241758242 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O X X O on move: O X X O O X X O on move: X X O X O O X X O on move: O X O X O X O X X O Episode 183, Total Reward: 1 Average Reward: 0.32786885245901637 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O X O O X on move: O X O X X O O X Episode 184, Total Reward: 1 Average Reward: 0.33152173913043476 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O X O X X X Episode 185, Total Reward: 1 Average Reward: 0.33513513513513515 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X on move: X O O X X X O O X on move: O O O X X X O O X X Episode 186, Total Reward: 0 Average Reward: 0.3333333333333333 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X O X on move: X X O X O O X on move: O X O X O O X X Episode 187, Total Reward: 1 Average Reward: 0.33689839572192515 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X O X X O O X on move: X X O X X O O X O on move: O X O X X O X O X O Episode 188, Total Reward: 0 Average Reward: 0.3351063829787234 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X Episode 189, Total Reward: 1 Average Reward: 0.3386243386243386 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X O X X on move: O O O X O X X X on move: X O O X O X X X O Episode 190, Total Reward: -1 Average Reward: 0.33157894736842103 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X X O X X O O on move: X O X X O X X O O Episode 191, Total Reward: -1 Average Reward: 0.32460732984293195 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X X O O O X X on move: X X X O O O O X X Episode 192, Total Reward: -1 Average Reward: 0.3177083333333333 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X X O O X O Episode 193, Total Reward: 1 Average Reward: 0.32124352331606215 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X X O X O O on move: O X X X O X O O Episode 194, Total Reward: 1 Average Reward: 0.3247422680412371 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X O X O O X on move: O X O X O X O X Episode 195, Total Reward: 1 Average Reward: 0.3282051282051282 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X on move: X O O X X O X O X on move: O X O O X X O X O X Episode 196, Total Reward: 1 Average Reward: 0.33163265306122447 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O O X O O X X X on move: X O X O O O X X X on move: O O X O O O X X X X Episode 197, Total Reward: 1 Average Reward: 0.3350253807106599 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X O X X O X O on move: O O X X X O X O on move: X O X X X O X O O Episode 198, Total Reward: -1 Average Reward: 0.3282828282828283 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X O X O O X X on move: O O X O O X X X Episode 199, Total Reward: 1 Average Reward: 0.3316582914572864 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X O X O X on move: O O X O X X O X on move: X O X O O X X O X on move: O O X X O O X X O X Episode 200, Total Reward: 1 Average Reward: 0.335 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X Episode 201, Total Reward: 1 Average Reward: 0.3383084577114428 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O X O Episode 202, Total Reward: -1 Average Reward: 0.3316831683168317 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X Episode 203, Total Reward: -1 Average Reward: 0.3251231527093596 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X X O O X on move: X O X X X O O O X on move: O O X X X X O O O X Episode 204, Total Reward: 0 Average Reward: 0.3235294117647059 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X O X X O X O on move: O X O X X O X O on move: X X O O X X O X O Episode 205, Total Reward: -1 Average Reward: 0.3170731707317073 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X O X O X X O on move: O X O X O X X O on move: X X O X O X X O O on move: O X O X O X X O O X Episode 206, Total Reward: 1 Average Reward: 0.32038834951456313 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O X O X X O on move: O O X O X X X O on move: X O O X O X X X O on move: O O O X O X X X X O Episode 207, Total Reward: 1 Average Reward: 0.32367149758454106 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X O X O X O X on move: O O X O X O X X on move: X O X O X O O X X on move: O X O X O X O O X X Episode 208, Total Reward: 1 Average Reward: 0.3269230769230769 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X on move: X X O O O X O X X on move: O X O O O X O X X X Episode 209, Total Reward: 1 Average Reward: 0.33014354066985646 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 210, Total Reward: -1 Average Reward: 0.3238095238095238 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O O X X O O X X on move: X O X X O O O X X on move: O O X X X O O O X X Episode 211, Total Reward: 0 Average Reward: 0.3222748815165877 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O X O X O on move: O X O X X O X O on move: X X O X X O X O O Episode 212, Total Reward: -1 Average Reward: 0.3160377358490566 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 213, Total Reward: -1 Average Reward: 0.30985915492957744 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X O X X O O on move: X X O X O X X O O Episode 214, Total Reward: -1 Average Reward: 0.3037383177570093 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X O X X X O O Episode 215, Total Reward: 1 Average Reward: 0.30697674418604654 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O Episode 216, Total Reward: 1 Average Reward: 0.3101851851851852 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X O X O O X X on move: O X O X O O X X on move: X X O X O O O X X Episode 217, Total Reward: -1 Average Reward: 0.30414746543778803 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X X O on move: O O O X X X X O on move: X O O O X X X X O on move: O O O X O X X X X O Episode 218, Total Reward: 1 Average Reward: 0.3073394495412844 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O X O X X O Episode 219, Total Reward: 1 Average Reward: 0.3105022831050228 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X on move: X O O X O X X X O on move: O O O X O X X X X O Episode 220, Total Reward: 1 Average Reward: 0.31363636363636366 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O O O X X X O X on move: X O O X X X O X O on move: O O O X X X X O X O Episode 221, Total Reward: 1 Average Reward: 0.3167420814479638 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X Episode 222, Total Reward: 1 Average Reward: 0.31981981981981983 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O O O X X X O X on move: X O O X X O X O X on move: O O X O X X O X O X Episode 223, Total Reward: 0 Average Reward: 0.3183856502242152 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O Episode 224, Total Reward: -1 Average Reward: 0.3125 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X O X O Episode 225, Total Reward: 1 Average Reward: 0.31555555555555553 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X O X on move: X O X X O O X on move: O O X X O O X X Episode 226, Total Reward: 1 Average Reward: 0.3185840707964602 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O X X O Episode 227, Total Reward: -1 Average Reward: 0.31277533039647576 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X O X on move: X X O O X O X on move: O X O O X O X X on move: X X O O O X O X X Episode 228, Total Reward: -1 Average Reward: 0.30701754385964913 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X O X O on move: X O X X X O O X O on move: O X O X X X O O X O Episode 229, Total Reward: 0 Average Reward: 0.3056768558951965 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X O X X X O O on move: X X O X O X X O O Episode 230, Total Reward: -1 Average Reward: 0.3 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X O X on move: X O X O X O X on move: O O X X O X O X on move: X O X X O X O X O Episode 231, Total Reward: -1 Average Reward: 0.2943722943722944 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O O X O O X X X on move: X O X O O X X O X on move: O O X O O X X X O X Episode 232, Total Reward: 0 Average Reward: 0.29310344827586204 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X on move: O X X O X O O X on move: X X O X O X O O X on move: O X O X O X O O X X Episode 233, Total Reward: 1 Average Reward: 0.296137339055794 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O O X on move: O X O X O O X X on move: X X O X O O O X X Episode 234, Total Reward: -1 Average Reward: 0.2905982905982906 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X on move: X X O O O X O X X on move: O X O O O X O X X X Episode 235, Total Reward: 1 Average Reward: 0.2936170212765957 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X O X O X X O on move: O O X O X X X O on move: X O X O X O X X O Episode 236, Total Reward: -1 Average Reward: 0.288135593220339 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X O O X X on move: X O X X O O X X O on move: O O X X O X O X X O Episode 237, Total Reward: 1 Average Reward: 0.2911392405063291 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X X O O X on move: X O O X X X O O X on move: O O O X X X O O X X Episode 238, Total Reward: 0 Average Reward: 0.28991596638655465 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O X O on move: O O X X X O X O on move: X O O X X X O X O on move: O O O X X X O X X O Episode 239, Total Reward: 1 Average Reward: 0.2928870292887029 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X O X X on move: O X O O X O X X on move: X X O O X O O X X on move: O X O O X X O O X X Episode 240, Total Reward: 1 Average Reward: 0.29583333333333334 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X on move: O X X X O O O X on move: X O X X X O O O X on move: O O X X X O O X O X Episode 241, Total Reward: 0 Average Reward: 0.2946058091286307 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X O X X O O X on move: O O X X X O O X on move: X O X X X O O O X on move: O O X X X O O O X X Episode 242, Total Reward: 0 Average Reward: 0.29338842975206614 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O O X X on move: O O X O O X X X on move: X O X O O X X X O on move: O O X O O X X X X O Episode 243, Total Reward: 1 Average Reward: 0.2962962962962963 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O X O X O X on move: X X O X O O X on move: O X X O X O O X on move: X X X O X O O O X Episode 244, Total Reward: -1 Average Reward: 0.29098360655737704 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O X X O on move: O O X O X X O X on move: X O X O X X O X O on move: O O X O X X X O X O Episode 245, Total Reward: 1 Average Reward: 0.2938775510204082 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O X O X O O X X on move: X X O X O O O X X on move: O X O X X O O O X X Episode 246, Total Reward: 0 Average Reward: 0.2926829268292683 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X on move: O X X X O O O X on move: X X X O X O O O X Episode 247, Total Reward: -1 Average Reward: 0.2874493927125506 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X O X X X O O on move: O O X X X X O O Episode 248, Total Reward: 1 Average Reward: 0.2903225806451613 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X O X O Episode 249, Total Reward: -1 Average Reward: 0.285140562248996 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X Episode 250, Total Reward: 1 Average Reward: 0.288 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O X X O on move: O O X O X X X O Episode 251, Total Reward: 1 Average Reward: 0.2908366533864542 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O O O X X X O X on move: X O O O X X X O X Episode 252, Total Reward: -1 Average Reward: 0.2857142857142857 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X O X O X O on move: O X O X X O X O on move: X X O X X O O X O on move: O X O X X O X O X O Episode 253, Total Reward: 0 Average Reward: 0.2845849802371542 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X O X on move: X X O X O O X on move: O X O X O O X X Episode 254, Total Reward: 1 Average Reward: 0.2874015748031496 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 255, Total Reward: -1 Average Reward: 0.2823529411764706 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X on move: X O O X O X O X X on move: O O O X X O X O X X Episode 256, Total Reward: 1 Average Reward: 0.28515625 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X Episode 257, Total Reward: 1 Average Reward: 0.28793774319066145 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O X O O O X X X Episode 258, Total Reward: 1 Average Reward: 0.29069767441860467 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X X O X O O on move: X X O X X O X O O Episode 259, Total Reward: -1 Average Reward: 0.2857142857142857 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O X O X O O X X on move: X O X O X O O X X on move: O O X O X X O O X X Episode 260, Total Reward: 1 Average Reward: 0.28846153846153844 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O O O X X on move: X X X O O O X O X on move: O X X O X O O X O X Episode 261, Total Reward: 1 Average Reward: 0.29118773946360155 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O O O X X on move: X X X O O O X O X Episode 262, Total Reward: -1 Average Reward: 0.2862595419847328 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X O O X X O on move: X X X O O X X O O on move: O X X O O X X X O O Episode 263, Total Reward: 0 Average Reward: 0.28517110266159695 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X O X O O X on move: O X X O X O O X Episode 264, Total Reward: 1 Average Reward: 0.2878787878787879 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X X O O on move: X O X X X O X O O on move: O O X X X X O X O O Episode 265, Total Reward: 1 Average Reward: 0.29056603773584905 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O X O X O X on move: X O X O X O X on move: O O X O X O X X on move: X O X O X O O X X on move: O O X O X O O X X X Episode 266, Total Reward: 1 Average Reward: 0.2932330827067669 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O X O X X X on move: X O O X O X X X O Episode 267, Total Reward: -1 Average Reward: 0.2883895131086142 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X on move: O X X O O X O X on move: X O X X O O X O X on move: O O X X X O O X O X Episode 268, Total Reward: 0 Average Reward: 0.2873134328358209 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X O X on move: X O X X O X O on move: O O X X O X X O on move: X O X X O X X O O Episode 269, Total Reward: -1 Average Reward: 0.2825278810408922 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X O X X X O O on move: O O X X X O X O Episode 270, Total Reward: 1 Average Reward: 0.2851851851851852 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O O X X on move: O X X O O O X X on move: X X X O O O O X X Episode 271, Total Reward: -1 Average Reward: 0.28044280442804426 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X O X O on move: O O X X X O X O on move: X O X X X O X O O on move: O O X X X X O X O O Episode 272, Total Reward: 1 Average Reward: 0.28308823529411764 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X O X O X O on move: O X O X O X X O on move: X X O X O O X X O on move: O X O X X O O X X O Episode 273, Total Reward: 1 Average Reward: 0.2857142857142857 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X O X O on move: O O X X X O X O Episode 274, Total Reward: 1 Average Reward: 0.28832116788321166 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X Episode 275, Total Reward: -1 Average Reward: 0.28363636363636363 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X X O on move: X O X O X X O Episode 276, Total Reward: -1 Average Reward: 0.27898550724637683 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O X O X X O on move: X X O X X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 277, Total Reward: -1 Average Reward: 0.2743682310469314 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X O X X O on move: O O X O X X X O on move: X O X O X X O X O on move: O X O X O X X O X O Episode 278, Total Reward: 0 Average Reward: 0.2733812949640288 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X X O O on move: X O X X X O X O O Episode 279, Total Reward: -1 Average Reward: 0.26881720430107525 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X O X O X O X Episode 280, Total Reward: -1 Average Reward: 0.2642857142857143 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O X O X O O X X on move: X X O X O O O X X Episode 281, Total Reward: -1 Average Reward: 0.2597864768683274 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O O X X O X X on move: X O O X X O O X X on move: O O O X X X O O X X Episode 282, Total Reward: 0 Average Reward: 0.25886524822695034 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X O X O on move: X O X X X O O X O on move: O O X X X O O X O X Episode 283, Total Reward: 0 Average Reward: 0.2579505300353357 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O O X X O X Episode 284, Total Reward: -1 Average Reward: 0.2535211267605634 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O X O X O X on move: X X O X O X O on move: O X O X X O X O Episode 285, Total Reward: 1 Average Reward: 0.256140350877193 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O Episode 286, Total Reward: 1 Average Reward: 0.25874125874125875 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O O O X on move: X X X X O O O X O on move: O X X X X O O O X O Episode 287, Total Reward: 1 Average Reward: 0.2613240418118467 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X O X X O X O Episode 288, Total Reward: -1 Average Reward: 0.2569444444444444 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X X O O O X on move: X O X X X O O O X on move: O O X X X X O O O X Episode 289, Total Reward: 0 Average Reward: 0.2560553633217993 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X X O X O on move: X O X X O X O on move: O O X X O X O X Episode 290, Total Reward: 1 Average Reward: 0.25862068965517243 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X O X X O on move: O O X O X X X O on move: X O X O X O X X O Episode 291, Total Reward: -1 Average Reward: 0.2542955326460481 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X on move: X X O O O X X X O on move: O X X O O O X X X O Episode 292, Total Reward: 0 Average Reward: 0.2534246575342466 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X X O O O X on move: X X O X X O O O X on move: O X O X X X O O O X Episode 293, Total Reward: 1 Average Reward: 0.25597269624573377 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O X O X on move: O X O O X X O X Episode 294, Total Reward: 1 Average Reward: 0.2585034013605442 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O O X X O O X X on move: X O X X O O X X O Episode 295, Total Reward: -1 Average Reward: 0.2542372881355932 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O X X O on move: O O X X O X X O on move: X O X X O O X X O on move: O O X X O X O X X O Episode 296, Total Reward: 1 Average Reward: 0.25675675675675674 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X Episode 297, Total Reward: 1 Average Reward: 0.25925925925925924 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O O X X on move: O O X O O X X X on move: X O X O O X X O X on move: O O X O O X X X O X Episode 298, Total Reward: 0 Average Reward: 0.25838926174496646 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X O X X X O O on move: X X O X X X O O O on move: O X O X X X O O X O Episode 299, Total Reward: 0 Average Reward: 0.25752508361204013 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O X O O X X X on move: X O X O O O X X X on move: O O X O O O X X X X Episode 300, Total Reward: 1 Average Reward: 0.26 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X X O O X O on move: X X O X X O O X O on move: O X O X X O O X X O Episode 301, Total Reward: 1 Average Reward: 0.26245847176079734 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O X O X O X X Episode 302, Total Reward: 1 Average Reward: 0.26490066225165565 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X on move: X O O O X X X O X Episode 303, Total Reward: -1 Average Reward: 0.2607260726072607 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X X O O X O on move: O X X X O O X O Episode 304, Total Reward: 1 Average Reward: 0.2631578947368421 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X O X on move: X X O X O X O on move: O X X O X O X O on move: X X X O O X O X O on move: O X X X O O X O X O Episode 305, Total Reward: 1 Average Reward: 0.26557377049180325 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O X O Episode 306, Total Reward: -1 Average Reward: 0.26143790849673204 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X Episode 307, Total Reward: -1 Average Reward: 0.25732899022801303 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O X O O X on move: O X O X X O O X on move: X X O X X O O X O on move: O X O X X X O O X O Episode 308, Total Reward: 0 Average Reward: 0.2564935064935065 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X X O O O X on move: X X X O X O O O X Episode 309, Total Reward: -1 Average Reward: 0.2524271844660194 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O X O X O X on move: X X O X O O X on move: O X X O X O O X Episode 310, Total Reward: 1 Average Reward: 0.25483870967741934 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O X O X X O on move: X X O O X X O on move: O X O O X X O X on move: X X O O X X O X O on move: O X O X O X X O X O Episode 311, Total Reward: 0 Average Reward: 0.2540192926045016 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O Episode 312, Total Reward: 1 Average Reward: 0.2564102564102564 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O Episode 313, Total Reward: 1 Average Reward: 0.25878594249201275 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X X O X O O on move: O X X X O X O O on move: X O X X X O X O O Episode 314, Total Reward: -1 Average Reward: 0.25477707006369427 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X O X O O X on move: O X O X X O O X on move: X X O X X O O O X on move: O X O X X O O O X X Episode 315, Total Reward: 0 Average Reward: 0.25396825396825395 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X O X O on move: O X O X X O X O on move: X X O X X O X O O Episode 316, Total Reward: -1 Average Reward: 0.25 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X Episode 317, Total Reward: -1 Average Reward: 0.24605678233438485 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X O X X O X O on move: X X O O X X O X O on move: O X X O O X X O X O Episode 318, Total Reward: 1 Average Reward: 0.24842767295597484 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O O X X on move: O X X O O O X X on move: X X X O O O O X X Episode 319, Total Reward: -1 Average Reward: 0.2445141065830721 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X O X O X on move: O O X O X X O X Episode 320, Total Reward: 1 Average Reward: 0.246875 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X O X on move: X O X X O O X on move: O O X X X O O X on move: X O X X X O O O X on move: O X O X X X O O O X Episode 321, Total Reward: 1 Average Reward: 0.24922118380062305 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O X O X on move: O O X O X X O X on move: X O X O O X X O X on move: O O X O O X X X O X Episode 322, Total Reward: 0 Average Reward: 0.2484472049689441 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X X O O X O on move: O X X X O O X O Episode 323, Total Reward: 1 Average Reward: 0.25077399380804954 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O O X X O O X X on move: X O X X O O X X O Episode 324, Total Reward: -1 Average Reward: 0.24691358024691357 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X O X on move: X O X X O O X on move: O X O X X O O X Episode 325, Total Reward: 1 Average Reward: 0.24923076923076923 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O X O on move: O O X X X O X O on move: X O X X X O X O O Episode 326, Total Reward: -1 Average Reward: 0.24539877300613497 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X O X X O O on move: X X X O O X X O O on move: O X X O O X X X O O Episode 327, Total Reward: 0 Average Reward: 0.24464831804281345 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X O X X O X O on move: X X O O X X O X O on move: O X O X O X X O X O Episode 328, Total Reward: 0 Average Reward: 0.24390243902439024 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X O X O O X X on move: O O X O O X X X Episode 329, Total Reward: 1 Average Reward: 0.24620060790273557 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O O O X X X O X Episode 330, Total Reward: 1 Average Reward: 0.24848484848484848 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X X O on move: O O O X X X X O Episode 331, Total Reward: 1 Average Reward: 0.25075528700906347 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O O X O X X on move: O O O X X O X X on move: X O O X X O X X O Episode 332, Total Reward: -1 Average Reward: 0.2469879518072289 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X X O O X on move: X O X X X O O O X on move: O O X X X X O O O X Episode 333, Total Reward: 0 Average Reward: 0.24624624624624625 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X X O O X O on move: O X X X O O X O Episode 334, Total Reward: 1 Average Reward: 0.24850299401197604 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X O X X O O on move: X X X O O X X O O on move: O X X X O O X X O O Episode 335, Total Reward: 1 Average Reward: 0.2507462686567164 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O X O O X on move: O X O X O X O X on move: X X O X O O X O X on move: O X O X O X O X O X Episode 336, Total Reward: 1 Average Reward: 0.25297619047619047 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O X X O on move: O O X X O X X O on move: X O X X O X X O O Episode 337, Total Reward: -1 Average Reward: 0.24925816023738873 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O O X X X O on move: O O O X X X O X on move: X O O O X X X O X on move: O O O X O X X X O X Episode 338, Total Reward: 1 Average Reward: 0.2514792899408284 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O O X X O on move: O X X O O X X O Episode 339, Total Reward: 1 Average Reward: 0.2536873156342183 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O X O O X on move: O X O X X O O X Episode 340, Total Reward: 1 Average Reward: 0.25588235294117645 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O X O O X X on move: X O X O X O O X X on move: O O X O X O O X X X Episode 341, Total Reward: 1 Average Reward: 0.25806451612903225 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X O X X O O X Episode 342, Total Reward: 1 Average Reward: 0.260233918128655 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X O X O X O X Episode 343, Total Reward: -1 Average Reward: 0.2565597667638484 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 344, Total Reward: -1 Average Reward: 0.25290697674418605 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X X O O Episode 345, Total Reward: 1 Average Reward: 0.25507246376811593 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X Episode 346, Total Reward: -1 Average Reward: 0.2514450867052023 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X Episode 347, Total Reward: 1 Average Reward: 0.25360230547550433 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X on move: X X O O O X O X X Episode 348, Total Reward: -1 Average Reward: 0.25 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X O X on move: X O O X X O X on move: O O O X X O X X on move: X O O X X O X X O on move: O O O X X X O X X O Episode 349, Total Reward: 1 Average Reward: 0.2521489971346705 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X O X O on move: O O X X X O X O Episode 350, Total Reward: 1 Average Reward: 0.2542857142857143 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X X O X X on move: X O O X X O O X X on move: O X O O X X O O X X Episode 351, Total Reward: 1 Average Reward: 0.2564102564102564 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O X O on move: O X X O O X X O Episode 352, Total Reward: 1 Average Reward: 0.2585227272727273 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O Episode 353, Total Reward: 1 Average Reward: 0.26062322946175637 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O O X O X X on move: O O O X X O X X Episode 354, Total Reward: 1 Average Reward: 0.2627118644067797 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X O X O O X on move: O X O X X O O X on move: X X O X O X O O X Episode 355, Total Reward: -1 Average Reward: 0.2591549295774648 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X X O O O X X on move: X X X O O O O X X Episode 356, Total Reward: -1 Average Reward: 0.2556179775280899 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O X O X O Episode 357, Total Reward: -1 Average Reward: 0.25210084033613445 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X X O O on move: X O X X X X O O O Episode 358, Total Reward: -1 Average Reward: 0.24860335195530725 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X O X O O on move: O X X X O X O O Episode 359, Total Reward: 1 Average Reward: 0.25069637883008355 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O O X O X Episode 360, Total Reward: -1 Average Reward: 0.24722222222222223 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O X O X X O on move: X X O O X X O on move: O X O O X X X O on move: X X O O O X X X O on move: O X O O O X X X X O Episode 361, Total Reward: 0 Average Reward: 0.24653739612188366 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X O X X O O X on move: O O X X O O X X on move: X O X X O O O X X on move: O O X X X O O O X X Episode 362, Total Reward: 0 Average Reward: 0.24585635359116023 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O X O X on move: O O X O X X O X on move: X O X O O X X O X on move: O O X O X O X X O X Episode 363, Total Reward: 0 Average Reward: 0.24517906336088155 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O O X X on move: O X O O X O X X Episode 364, Total Reward: 1 Average Reward: 0.24725274725274726 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O O O X X on move: X X X O O O O X X on move: O X X O O X O O X X Episode 365, Total Reward: 1 Average Reward: 0.2493150684931507 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X O X O O X on move: O X X O X O O X Episode 366, Total Reward: 1 Average Reward: 0.25136612021857924 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X X O X O O on move: O X X O X O O X on move: X X X O X O O O X on move: O X X O X O O X O X Episode 367, Total Reward: 1 Average Reward: 0.25340599455040874 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O X O X X O X on move: X O X O X X O X O on move: O O X O X X X O X O Episode 368, Total Reward: 1 Average Reward: 0.2554347826086957 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X X O Episode 369, Total Reward: -1 Average Reward: 0.25203252032520324 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X O X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 370, Total Reward: -1 Average Reward: 0.24864864864864866 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X X O X O on move: X X O X O X O on move: O X O X O X X O Episode 371, Total Reward: 1 Average Reward: 0.25067385444743934 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O X X O on move: O O X X O X X O Episode 372, Total Reward: 1 Average Reward: 0.25268817204301075 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O X O X X Episode 373, Total Reward: 1 Average Reward: 0.2546916890080429 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X O X O O X on move: O X O X X O O X on move: X O X O X X O O X on move: O O X O X X X O O X Episode 374, Total Reward: 1 Average Reward: 0.25668449197860965 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X Episode 375, Total Reward: -1 Average Reward: 0.25333333333333335 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X on move: X X O O O X X X O on move: O X O O O X X X X O Episode 376, Total Reward: 0 Average Reward: 0.2526595744680851 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X Episode 377, Total Reward: 1 Average Reward: 0.2546419098143236 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X Episode 378, Total Reward: 1 Average Reward: 0.2566137566137566 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O O O X X O X X on move: X O O X X O X O X on move: O O X O X X O X O X Episode 379, Total Reward: 0 Average Reward: 0.2559366754617414 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X O X X O O on move: X X O X O X X O O on move: O X O X O X X X O O Episode 380, Total Reward: 1 Average Reward: 0.2578947368421053 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X O X on move: X X O O X O X Episode 381, Total Reward: -1 Average Reward: 0.2545931758530184 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X O X X O O X on move: O O X X X O O X Episode 382, Total Reward: 1 Average Reward: 0.25654450261780104 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X X O X X O O Episode 383, Total Reward: 1 Average Reward: 0.2584856396866841 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X Episode 384, Total Reward: 1 Average Reward: 0.2604166666666667 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X O X X on move: O X O O X O X X on move: X X O O O X O X X Episode 385, Total Reward: -1 Average Reward: 0.2571428571428571 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X X O O X O Episode 386, Total Reward: 1 Average Reward: 0.25906735751295334 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X X O O X O X on move: O X O O X O X X Episode 387, Total Reward: 1 Average Reward: 0.26098191214470284 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O X O on move: O X X O O X X O Episode 388, Total Reward: 1 Average Reward: 0.26288659793814434 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X on move: O X X O O O X X on move: X X X O O O O X X Episode 389, Total Reward: -1 Average Reward: 0.2596401028277635 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X X O on move: O O O X X X X O Episode 390, Total Reward: 1 Average Reward: 0.26153846153846155 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O O X O X X O X on move: X O X O O X X O X on move: O O X X O O X X O X Episode 391, Total Reward: 1 Average Reward: 0.26342710997442453 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X O X X X O O on move: O O X X X X O O on move: X O X X X X O O O Episode 392, Total Reward: -1 Average Reward: 0.2602040816326531 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X O X X X O O Episode 393, Total Reward: 1 Average Reward: 0.26208651399491095 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X O X X O O X on move: O O X X X O O X on move: X O X X X O O O X on move: O X O X X X O O O X Episode 394, Total Reward: 1 Average Reward: 0.2639593908629442 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X O X O on move: O X O X O X X O on move: X X O O X O X X O Episode 395, Total Reward: -1 Average Reward: 0.2607594936708861 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X O X X O O on move: O X O X X O X O on move: X X O O X X O X O on move: O X X O O X X O X O Episode 396, Total Reward: 1 Average Reward: 0.26262626262626265 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O X O O O X X X on move: X X O O O O X X X on move: O X O O O O X X X X Episode 397, Total Reward: 1 Average Reward: 0.26448362720403024 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X O X O X Episode 398, Total Reward: 1 Average Reward: 0.2663316582914573 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X X O X O O Episode 399, Total Reward: 1 Average Reward: 0.2681704260651629 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X O O X X on move: X O X O X O O X X on move: O O X O X O O X X X Episode 400, Total Reward: 1 Average Reward: 0.27 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X X O X O O X on move: O X X O X O O X on move: X X X O X O O O X Episode 401, Total Reward: -1 Average Reward: 0.26683291770573564 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X O X X on move: O O O X X O X X on move: X O O O X X O X X Episode 402, Total Reward: -1 Average Reward: 0.263681592039801 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X X O X O on move: X X O X O X O on move: O X O X X O X O on move: X X O X O X O X O on move: O X O X X O X O X O Episode 403, Total Reward: 0 Average Reward: 0.2630272952853598 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O X O O X X O X Episode 404, Total Reward: 1 Average Reward: 0.26485148514851486 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O O X O X O X X Episode 405, Total Reward: 1 Average Reward: 0.26666666666666666 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O X O O Episode 406, Total Reward: 1 Average Reward: 0.2684729064039409 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X O X X O X O on move: O O X X X O X O on move: X O X X X O O X O Episode 407, Total Reward: -1 Average Reward: 0.26535626535626533 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X X O X X O O Episode 408, Total Reward: 1 Average Reward: 0.26715686274509803 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O O O X on move: X O X X X O O O X on move: O X O X X X O O O X Episode 409, Total Reward: 1 Average Reward: 0.26894865525672373 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X X O X O on move: X O X X O X O on move: O O X X X O X O on move: X O O X X X O X O on move: O O O X X X O X X O Episode 410, Total Reward: 1 Average Reward: 0.2707317073170732 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X X O X O on move: X O X X O X O on move: O O X X X O X O on move: X O X X X O O X O on move: O O X X X X O O X O Episode 411, Total Reward: 1 Average Reward: 0.2725060827250608 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X O X O on move: O X O X O X X O Episode 412, Total Reward: 1 Average Reward: 0.27427184466019416 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X O X X O X O Episode 413, Total Reward: -1 Average Reward: 0.2711864406779661 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X Episode 414, Total Reward: 1 Average Reward: 0.27294685990338163 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O X O on move: O X X O O X O X Episode 415, Total Reward: 1 Average Reward: 0.2746987951807229 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O X O X O X X on move: X O X O O X O X X Episode 416, Total Reward: -1 Average Reward: 0.27163461538461536 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X O X X O O X on move: O O X X X O O X on move: X O X X X O O O X on move: O O X X X O O O X X Episode 417, Total Reward: 0 Average Reward: 0.2709832134292566 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O Episode 418, Total Reward: 1 Average Reward: 0.2727272727272727 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O X O Episode 419, Total Reward: -1 Average Reward: 0.26968973747016706 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X Episode 420, Total Reward: 1 Average Reward: 0.2714285714285714 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X O X O X O X on move: O O X O X X O X on move: X O O X O X X O X on move: O O X O X O X X O X Episode 421, Total Reward: 0 Average Reward: 0.27078384798099764 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O O X X X X on move: X O O O O X X X X Episode 422, Total Reward: -1 Average Reward: 0.2677725118483412 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X Episode 423, Total Reward: 1 Average Reward: 0.2695035460992908 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X Episode 424, Total Reward: 1 Average Reward: 0.27122641509433965 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X on move: O X X O O O X X on move: X X X O O O X X O on move: O X X O O O X X O X Episode 425, Total Reward: 0 Average Reward: 0.27058823529411763 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X X O X on move: X O X X O O X on move: O O X X O O X X on move: X O O X X O O X X on move: O O X O X X O O X X Episode 426, Total Reward: 1 Average Reward: 0.27230046948356806 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O X O O X X on move: O X O X O O X X Episode 427, Total Reward: 1 Average Reward: 0.27400468384074944 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O Episode 428, Total Reward: 1 Average Reward: 0.2757009345794392 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X O X on move: X O X X O O X on move: O X O X X O O X on move: X X O X X O O O X on move: O X O X X X O O O X Episode 429, Total Reward: 1 Average Reward: 0.2773892773892774 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X O O X on move: X O X X X O O O X on move: O O X X X X O O O X Episode 430, Total Reward: 0 Average Reward: 0.27674418604651163 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X Episode 431, Total Reward: 1 Average Reward: 0.27842227378190254 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O Episode 432, Total Reward: 1 Average Reward: 0.2800925925925926 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X O X O on move: X O O X X X O X O on move: O O O X X X O X X O Episode 433, Total Reward: 1 Average Reward: 0.2817551963048499 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X Episode 434, Total Reward: 1 Average Reward: 0.2834101382488479 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O O X O on move: O X X O O X O X on move: X X X O O O X O X on move: O X X O O O X X O X Episode 435, Total Reward: 0 Average Reward: 0.2827586206896552 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X X O X O O on move: O X X X O X O O on move: X O X X X O X O O on move: O O X X X O X O O X Episode 436, Total Reward: 1 Average Reward: 0.28440366972477066 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O X O on move: O X O X X O X O on move: X X O O X X O X O on move: O X O O X X X O X O Episode 437, Total Reward: 1 Average Reward: 0.28604118993135014 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O X O X X O on move: X X O X X O O Episode 438, Total Reward: -1 Average Reward: 0.2831050228310502 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O X O O X on move: X X X O O X O O X on move: O X X X O O X O O X Episode 439, Total Reward: 1 Average Reward: 0.2847380410022779 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X O X X O X O Episode 440, Total Reward: -1 Average Reward: 0.2818181818181818 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O Episode 441, Total Reward: 1 Average Reward: 0.2834467120181406 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O O X O X on move: O X X O O X O X on move: X X X O O O X O X on move: O X X O X O O X O X Episode 442, Total Reward: 1 Average Reward: 0.2850678733031674 on move: O X on move: X X O on move: O X O X on move: X X O X O on move: O X O X X O on move: X O X O X X O on move: O X O X O X X O Episode 443, Total Reward: 1 Average Reward: 0.2866817155756208 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X on move: X O O X X O X O X on move: O O O X X X O X O X Episode 444, Total Reward: 1 Average Reward: 0.2882882882882883 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O O X X O on move: O X O O X X X O on move: X X O O O X X X O on move: O X O O X O X X X O Episode 445, Total Reward: 1 Average Reward: 0.2898876404494382 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X X O O O X Episode 446, Total Reward: 1 Average Reward: 0.2914798206278027 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X O X O X O X on move: O O X O X X O X Episode 447, Total Reward: 1 Average Reward: 0.2930648769574944 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X Episode 448, Total Reward: 1 Average Reward: 0.29464285714285715 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X O X on move: X O O X X O X on move: O O O X X X O X Episode 449, Total Reward: 1 Average Reward: 0.2962138084632517 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X O X O X O X on move: O O X O X X O X Episode 450, Total Reward: 1 Average Reward: 0.29777777777777775 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O X O X O X X on move: X O X O X O O X X on move: O O X O X O O X X X Episode 451, Total Reward: 1 Average Reward: 0.29933481152993346 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X O X O X O X Episode 452, Total Reward: -1 Average Reward: 0.29646017699115046 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O X O O X X on move: X X O X O O O X X Episode 453, Total Reward: -1 Average Reward: 0.293598233995585 on move: O X on move: X O X on move: O X O X on move: X X O X O on move: O X X O X O on move: X X X O X O O on move: O X X O X X O O on move: X X X O O X X O O on move: O X X O O X X O O X Episode 454, Total Reward: 1 Average Reward: 0.29515418502202645 on move: O X on move: X O X on move: O X O X on move: X O X O X on move: O X O X O X Episode 455, Total Reward: 1 Average Reward: 0.2967032967032967 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O O X X on move: O O X X O O X X on move: X O X X O O O X X on move: O O X X X O O O X X Episode 456, Total Reward: 0 Average Reward: 0.29605263157894735 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X O X on move: X O X O X O X on move: O O X O X O X X Episode 457, Total Reward: 1 Average Reward: 0.2975929978118162 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O on move: X O O X X X O on move: O O O X X X X O Episode 458, Total Reward: 1 Average Reward: 0.29912663755458513 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O X O O X X O X Episode 459, Total Reward: 1 Average Reward: 0.3006535947712418 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O O X Episode 460, Total Reward: -1 Average Reward: 0.29782608695652174 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O Episode 461, Total Reward: -1 Average Reward: 0.2950108459869848 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O Episode 462, Total Reward: -1 Average Reward: 0.2922077922077922 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X O X on move: X O O X X O X on move: O O O X X O X X on move: X O O O X X O X X Episode 463, Total Reward: -1 Average Reward: 0.2894168466522678 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O X X X O O on move: O O X X X O O X Episode 464, Total Reward: 1 Average Reward: 0.29094827586206895 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X O X on move: X X O O X O X on move: O X X O O X O X on move: X X X O O O X O X Episode 465, Total Reward: -1 Average Reward: 0.28817204301075267 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X X O X on move: O O O X X O X X on move: X O O X O X O X X Episode 466, Total Reward: -1 Average Reward: 0.2854077253218884 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X Episode 467, Total Reward: 1 Average Reward: 0.28693790149892934 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X O X O O X X on move: O O X O O X X X Episode 468, Total Reward: 1 Average Reward: 0.28846153846153844 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X O X X on move: X O O X O X X on move: O O O X O X X X on move: X O O X O X X X O Episode 469, Total Reward: -1 Average Reward: 0.2857142857142857 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X on move: X O X O O X X on move: O O X O O X X X on move: X O X O O O X X X on move: O O X O O O X X X X Episode 470, Total Reward: 1 Average Reward: 0.2872340425531915 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X Episode 471, Total Reward: 1 Average Reward: 0.28874734607218683 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X Episode 472, Total Reward: -1 Average Reward: 0.2860169491525424 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O O X on move: X X X O O X O on move: O X X O O X X O on move: X X O X O O X X O on move: O X O X O O X X X O Episode 473, Total Reward: 0 Average Reward: 0.2854122621564482 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O X O X X X Episode 474, Total Reward: 1 Average Reward: 0.2869198312236287 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X O O X O on move: X X X X O O X O O on move: O X X X X O O X O O Episode 475, Total Reward: 1 Average Reward: 0.28842105263157897 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X O X X O O X on move: O O X X X O O X on move: X O X O X X O O X Episode 476, Total Reward: -1 Average Reward: 0.2857142857142857 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O Episode 477, Total Reward: 1 Average Reward: 0.28721174004192873 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O O X X X on move: O O O O X X X X Episode 478, Total Reward: 1 Average Reward: 0.28870292887029286 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X Episode 479, Total Reward: 1 Average Reward: 0.29018789144050106 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X O X X O O X on move: O O X X O X O X Episode 480, Total Reward: 1 Average Reward: 0.2916666666666667 on move: O X on move: X X O on move: O X O X on move: X O X O X on move: O O X X O X on move: X O X X O X O on move: O O X X X O X O on move: X O O X X X O X O on move: O O O X X X X O X O Episode 481, Total Reward: 1 Average Reward: 0.29313929313929316 on move: O X on move: X O X on move: O O X X on move: X O X X O on move: O O X X X O Episode 482, Total Reward: 1 Average Reward: 0.2946058091286307 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X X O O on move: X X X X O O O on move: O X X X X O O O on move: X O X X X X O O O on move: O O X X X X O O X O Episode 483, Total Reward: 1 Average Reward: 0.29606625258799174 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O X O X on move: O X O X O X O X Episode 484, Total Reward: 1 Average Reward: 0.2975206611570248 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O O X X X Episode 485, Total Reward: 1 Average Reward: 0.29896907216494845 on move: O X on move: X X O on move: O X X O on move: X X X O O on move: O X X O X O on move: X X X O X O O on move: O X X O X O O X on move: X X X O O X O O X on move: O X X O O X X O O X Episode 486, Total Reward: 1 Average Reward: 0.3004115226337449 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O O X X X O on move: O O X O X X X O on move: X O X O X X O X O on move: O O X O X X O X O X Episode 487, Total Reward: 0 Average Reward: 0.2997946611909651 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X O X X O O X on move: O O X X O X O X Episode 488, Total Reward: 1 Average Reward: 0.3012295081967213 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O O X X X on move: X O O X O X X on move: O O X O X O X X Episode 489, Total Reward: 1 Average Reward: 0.30265848670756645 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O O X O X X Episode 490, Total Reward: 1 Average Reward: 0.3040816326530612 on move: O X on move: X X O on move: O X X O on move: X X O X O on move: O X O X X O on move: X X O X X O O on move: O X X O X X O O on move: X X X O X X O O O Episode 491, Total Reward: -1 Average Reward: 0.3014256619144603 on move: O X on move: X O X on move: O O X X on move: X O O X X on move: O X O O X X on move: X X O O X O X on move: O X X O O X O X on move: X X O X O O X O X on move: O X O X O O X O X X Episode 492, Total Reward: 1 Average Reward: 0.30284552845528456 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O X O X on move: X X O X O X O on move: O X O X X O X O on move: X X O X X O X O O Episode 493, Total Reward: -1 Average Reward: 0.3002028397565923 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X O X O O X on move: O X O X X O O X on move: X X O X X O O X O on move: O X O X X X O O X O Episode 494, Total Reward: 0 Average Reward: 0.29959514170040485 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O X O X O X on move: X O X O X O X on move: O O X X O X O X on move: X O X X O O X O X on move: O O X X X O O X O X Episode 495, Total Reward: 0 Average Reward: 0.298989898989899 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X O O X X on move: X X O O O X X on move: O X O O X O X X Episode 496, Total Reward: 1 Average Reward: 0.3004032258064516 on move: O X on move: X X O on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O O X O X Episode 497, Total Reward: 1 Average Reward: 0.30181086519114686 on move: O X on move: X O X on move: O O X X on move: X O X O X on move: O O X O X X on move: X O X O O X X Episode 498, Total Reward: -1 Average Reward: 0.2991967871485944 on move: O X on move: X X O on move: O X X O on move: X O X X O on move: O O X X X O on move: X O O X X X O on move: O O O X X X O X on move: X O O O X X X O X Episode 499, Total Reward: -1 Average Reward: 0.2965931863727455 on move: O X on move: X O X on move: O X O X on move: X X O O X on move: O X X O O X on move: X X X O O O X on move: O X X O X O O X on move: X X X O X O O O X Episode 500, Total Reward: -1 Average Reward: 0.294