270 KiB
270 KiB
Лабораторная работа 6¶
Крестики-нолики https://github.com/nczempin/gym-tic-tac-toe/tree/master
Перевод среды на Gymnasium¶
In [11]:
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 # p - игрок (1 или -1), square - номер клетки
board = self.state['board']
proposed = board[square]
om = self.state['on_move']
if proposed != 0: # Клетка уже занята
print(f"Незаконный ход: Квадрат {square} уже занят.")
done = True
reward = -1 * om
if p != om: # Не тот игрок на ходу
print(f"Незаконный ход: игрок {p} не находится в движении")
done = True
reward = -1 * om
else:
board[square] = p
self.state['on_move'] = -p
for i in range(3):
# Горизонтали и вертикали
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
# Диагонали
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 [12]:
import random
class RandomTicTacToeAgent:
def __init__(self, symbol):
self.symbol = symbol # Символ игрока (1 - X, -1 - O
def get_action(self, moves):
return random.choice(moves) # Выбираем случайный ход из доступных
Основной цикл обучения¶
In [13]:
env = TicTacToeEnv()
agent = RandomTicTacToeAgent(symbol=1)
num_episodes = 400
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
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
X
O X O
on move: X
X X O
O X
O X O
on move: O
X X O
O X X
O X O
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
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
on move: O
X O O
O X X
X O X
Episode 2, Total Reward: 1
Average Reward: 1.0
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 3, 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 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 4, 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
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 5, Total Reward: 1
Average Reward: 1.0
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
X O O
X X
X O
on move: X
X O O
X X O
X O
Episode 6, Total Reward: -1
Average Reward: 0.6666666666666666
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 7, Total Reward: 1
Average Reward: 0.7142857142857143
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
on move: X
O X O
O O X
X X
on move: O
O X O
O O X
X X X
Episode 8, Total Reward: 1
Average Reward: 0.75
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 O
X X X
O O
Episode 9, Total Reward: 1
Average Reward: 0.7777777777777778
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 10, Total Reward: 1
Average Reward: 0.8
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 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 11, Total Reward: 1
Average Reward: 0.8181818181818182
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 O X
on move: O
X
X O X
O O X
on move: X
X O
X O X
O O X
Episode 12, Total Reward: -1
Average Reward: 0.6666666666666666
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
O X
X X O
on move: O
O O X
O X X
X X O
Episode 13, Total Reward: 1
Average Reward: 0.6923076923076923
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
Episode 14, Total Reward: 1
Average Reward: 0.7142857142857143
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 15, Total Reward: 1
Average Reward: 0.7333333333333333
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 X
O X
on move: O
X O X
O O X
O X X
Episode 16, Total Reward: 1
Average Reward: 0.75
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 17, Total Reward: 1
Average Reward: 0.7647058823529411
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
Episode 18, Total Reward: -1
Average Reward: 0.6666666666666666
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
X O
X O
X O X
on move: X
O X O
X O
X O X
on move: O
O X O
X O X
X O X
Episode 19, Total Reward: 0
Average Reward: 0.631578947368421
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 O
X X O
X X
Episode 20, Total Reward: -1
Average Reward: 0.55
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 X
O O
X X O
on move: X
X X
O O O
X X O
Episode 21, Total Reward: -1
Average Reward: 0.47619047619047616
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
X O X
X O
Episode 22, Total Reward: -1
Average Reward: 0.4090909090909091
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
Episode 23, Total Reward: 1
Average Reward: 0.43478260869565216
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 24, Total Reward: -1
Average Reward: 0.375
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 25, Total Reward: 1
Average Reward: 0.4
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 X
O X
X O
on move: X
O X X
O O X
X O
Episode 26, Total Reward: -1
Average Reward: 0.34615384615384615
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
on move: O
O O X
O X X
X O X
Episode 27, Total Reward: 1
Average Reward: 0.37037037037037035
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
O X
X O X
O
on move: O
O X
X O X
O X
on move: X
O X O
X O X
O X
on move: O
O X O
X O X
X O X
Episode 28, Total Reward: 0
Average Reward: 0.35714285714285715
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 29, Total Reward: -1
Average Reward: 0.3103448275862069
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 30, 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
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 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 31, Total Reward: 1
Average Reward: 0.3548387096774194
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 X
O X
X O
on move: X
O X X
O O X
X O
Episode 32, 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
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
X X O
X O O
O X
Episode 33, Total Reward: -1
Average Reward: 0.2727272727272727
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
Episode 34, Total Reward: -1
Average Reward: 0.23529411764705882
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 35, Total Reward: 1
Average Reward: 0.2571428571428571
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 36, Total Reward: 1
Average Reward: 0.2777777777777778
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
Episode 37, Total Reward: 1
Average Reward: 0.2972972972972973
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 X O
X X
Episode 38, Total Reward: 1
Average Reward: 0.3157894736842105
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 39, Total Reward: -1
Average Reward: 0.28205128205128205
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 X
O X
on move: X
X O O
O X X
O X
on move: O
X O O
O X X
O X X
Episode 40, Total Reward: 1
Average Reward: 0.3
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
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 41, Total Reward: 1
Average Reward: 0.3170731707317073
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 42, 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
X O
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 43, Total Reward: 1
Average Reward: 0.3023255813953488
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 44, Total Reward: 1
Average Reward: 0.3181818181818182
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 X O
X X
X O
on move: X
O X O
X O X
X O
Episode 45, 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
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
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 46, Total Reward: 0
Average Reward: 0.2826086956521739
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
Episode 47, Total Reward: 1
Average Reward: 0.2978723404255319
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
O X
O
X 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 O X
X X O
X O X
Episode 48, Total Reward: 1
Average Reward: 0.3125
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
Episode 49, Total Reward: 1
Average Reward: 0.32653061224489793
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 50, Total Reward: -1
Average Reward: 0.3
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
X O O
O O X
on move: O
X X X
X O O
O O X
Episode 51, Total Reward: 1
Average Reward: 0.3137254901960784
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 52, 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
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 53, Total Reward: 1
Average Reward: 0.3018867924528302
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
Episode 54, Total Reward: 1
Average Reward: 0.3148148148148148
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 55, Total Reward: 1
Average Reward: 0.32727272727272727
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
on move: X
O X O
X O X
X O
on move: O
O X O
X O X
X O X
Episode 56, Total Reward: 0
Average Reward: 0.32142857142857145
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
O X
X O O
O X X
on move: O
O X X
X O O
O X X
Episode 57, Total Reward: 0
Average Reward: 0.3157894736842105
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 X
O O
X O X
on move: X
X X
O O O
X O X
Episode 58, Total Reward: -1
Average Reward: 0.29310344827586204
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
O X
O O X
Episode 59, Total Reward: -1
Average Reward: 0.2711864406779661
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
on move: X
O X
O X O
O X X
on move: O
X O X
O X O
O X X
Episode 60, Total Reward: 1
Average Reward: 0.2833333333333333
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 X O
X
O X X
on move: X
O X O
X O
O X X
Episode 61, Total Reward: -1
Average Reward: 0.26229508196721313
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 62, Total Reward: 0
Average Reward: 0.25806451612903225
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
Episode 63, Total Reward: 1
Average Reward: 0.2698412698412698
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 64, Total Reward: 1
Average Reward: 0.28125
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 65, Total Reward: 1
Average Reward: 0.2923076923076923
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 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 66, Total Reward: 0
Average Reward: 0.2878787878787879
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 O X
X
O O X
Episode 67, Total Reward: 1
Average Reward: 0.29850746268656714
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 68, Total Reward: -1
Average Reward: 0.27941176470588236
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 O
X X
O X X
Episode 69, Total Reward: -1
Average Reward: 0.2608695652173913
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
X O
X X
Episode 70, 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
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 71, Total Reward: 1
Average Reward: 0.28169014084507044
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 O
X X
Episode 72, Total Reward: -1
Average Reward: 0.2638888888888889
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
on move: X
X X O
O X
O O X
on move: O
X X O
O X X
O O X
Episode 73, Total Reward: 1
Average Reward: 0.273972602739726
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 O
X X O
O X X
on move: O
X O O
X X O
O X X
Episode 74, Total Reward: 1
Average Reward: 0.28378378378378377
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 75, Total Reward: 1
Average Reward: 0.29333333333333333
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 76, Total Reward: 1
Average Reward: 0.3026315789473684
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 O
X
O X
on move: O
O X O
X X
O X
on move: X
O X O
X O X
O X
Episode 77, 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
Episode 78, Total Reward: 1
Average Reward: 0.2948717948717949
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 79, Total Reward: 1
Average Reward: 0.3037974683544304
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 80, Total Reward: 1
Average Reward: 0.3125
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 81, Total Reward: -1
Average Reward: 0.2962962962962963
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
X O X
on move: O
X X O
O O X
X O X
Episode 82, Total Reward: 0
Average Reward: 0.2926829268292683
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 83, Total Reward: 1
Average Reward: 0.30120481927710846
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 O
X X
X O O
on move: O
O X O
X X X
X O O
Episode 84, Total Reward: 1
Average Reward: 0.30952380952380953
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 O
X X O
X O X
on move: O
O O X
X X O
X O X
Episode 85, Total Reward: 1
Average Reward: 0.3176470588235294
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 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 86, Total Reward: 0
Average Reward: 0.313953488372093
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
X O O
X 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 87, Total Reward: 0
Average Reward: 0.3103448275862069
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
X O
O X
on move: X
O X X
X O
O X O
Episode 88, Total Reward: -1
Average Reward: 0.29545454545454547
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
on move: X
X O X
X X O
O O
on move: O
X O X
X X O
X O O
Episode 89, Total Reward: 1
Average Reward: 0.30337078651685395
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 90, Total Reward: -1
Average Reward: 0.28888888888888886
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 O
X X O
X O
Episode 91, Total Reward: -1
Average Reward: 0.27472527472527475
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 92, Total Reward: 1
Average Reward: 0.2826086956521739
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 93, Total Reward: 1
Average Reward: 0.2903225806451613
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 X
O O O
Episode 94, Total Reward: -1
Average Reward: 0.2765957446808511
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 95, Total Reward: 0
Average Reward: 0.2736842105263158
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 96, Total Reward: 1
Average Reward: 0.28125
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
Episode 97, Total Reward: 1
Average Reward: 0.28865979381443296
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 O X
O O X
on move: O
O X X
X O X
O O X
Episode 98, Total Reward: 1
Average Reward: 0.29591836734693877
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
O X
on move: O
O X O
X X O
O X X
Episode 99, Total Reward: 1
Average Reward: 0.30303030303030304
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
O X
O O X
X X O
on move: O
X O X
O O X
X X O
Episode 100, Total Reward: 0
Average Reward: 0.3
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
Episode 101, Total Reward: 1
Average Reward: 0.3069306930693069
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 102, Total Reward: 1
Average Reward: 0.3137254901960784
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
on move: X
O X O
X O O
X X
on move: O
O X O
X O O
X X X
Episode 103, 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
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 104, Total Reward: -1
Average Reward: 0.3076923076923077
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 105, Total Reward: 1
Average Reward: 0.3142857142857143
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 O X
X X
on move: O
X O O
O O X
X X X
Episode 106, Total Reward: 1
Average Reward: 0.32075471698113206
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 X O
X X
Episode 107, Total Reward: 1
Average Reward: 0.32710280373831774
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 108, 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 X
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
on move: X
X O X
X X O
O O
on move: O
X O X
X X O
O X O
Episode 109, Total Reward: 0
Average Reward: 0.3302752293577982
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 110, Total Reward: 1
Average Reward: 0.33636363636363636
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
Episode 111, Total Reward: 1
Average Reward: 0.34234234234234234
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 112, Total Reward: 1
Average Reward: 0.3482142857142857
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 X
O X X
O X
on move: X
O X
O X X
O X O
on move: O
X O X
O X X
O X O
Episode 113, Total Reward: 0
Average Reward: 0.34513274336283184
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 114, 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 O
X
O O
on move: O
X X O
X X
O O
on move: X
X X O
X O X
O O
Episode 115, Total Reward: -1
Average Reward: 0.3217391304347826
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 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
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 O
X X O
Episode 117, Total Reward: 1
Average Reward: 0.3162393162393162
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 O X
X O
Episode 118, Total Reward: -1
Average Reward: 0.3050847457627119
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
O X 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
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
on move: X
X O X
O O X
X O
on move: O
X O X
O O X
X X O
Episode 120, Total Reward: 0
Average Reward: 0.2916666666666667
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 O
X X
Episode 121, Total Reward: 1
Average Reward: 0.2975206611570248
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 122, Total Reward: 1
Average Reward: 0.30327868852459017
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 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 123, Total Reward: 1
Average Reward: 0.3089430894308943
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
X O
X O X
Episode 124, Total Reward: 1
Average Reward: 0.31451612903225806
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
Episode 125, Total Reward: 1
Average Reward: 0.32
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
Episode 126, Total Reward: 1
Average Reward: 0.3253968253968254
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
Episode 127, Total Reward: 1
Average Reward: 0.33070866141732286
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 128, Total Reward: 1
Average Reward: 0.3359375
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
X O
on move: O
X X
O X O
X O
on move: X
X X
O X O
X O O
on move: O
X X X
O X O
X O O
Episode 129, Total Reward: 1
Average Reward: 0.34108527131782945
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 O O
X X X
O
Episode 130, Total Reward: 1
Average Reward: 0.34615384615384615
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
X X
X O X
O O O
Episode 131, Total Reward: -1
Average Reward: 0.33587786259541985
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 X O
X O
X O
Episode 132, Total Reward: 1
Average Reward: 0.3409090909090909
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
O X
X X O
O X O
on move: O
X O X
X X O
O X O
Episode 133, Total Reward: 0
Average Reward: 0.3383458646616541
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 X O
Episode 134, Total Reward: -1
Average Reward: 0.3283582089552239
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
on move: X
X O
X X O
O X O
Episode 135, Total Reward: -1
Average Reward: 0.31851851851851853
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 O
X X
O O X
on move: O
O X O
X X X
O O X
Episode 136, Total Reward: 1
Average Reward: 0.3235294117647059
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 137, Total Reward: -1
Average Reward: 0.31386861313868614
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
X O O
on move: O
O O X
X X X
X O O
Episode 138, Total Reward: 1
Average Reward: 0.3188405797101449
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
Episode 139, Total Reward: 1
Average Reward: 0.3237410071942446
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
X O
X O
Episode 140, Total Reward: 1
Average Reward: 0.32857142857142857
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
Episode 141, 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
Episode 142, Total Reward: 1
Average Reward: 0.3380281690140845
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
Episode 143, Total Reward: -1
Average Reward: 0.32867132867132864
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 144, 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
X
O X X
on move: X
O
O X
O X X
Episode 145, Total Reward: -1
Average Reward: 0.32413793103448274
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 X O
Episode 146, Total Reward: 1
Average Reward: 0.3287671232876712
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
X O
on move: O
X O X
O X O
X X O
Episode 147, 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
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
O X
X O X
X O O
Episode 148, Total Reward: -1
Average Reward: 0.32432432432432434
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 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 O X
Episode 149, Total Reward: 0
Average Reward: 0.3221476510067114
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
X O 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 150, Total Reward: 0
Average Reward: 0.32
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 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 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 X
X O O
X X
on move: O
O O X
X O O
X X X
Episode 152, Total Reward: 1
Average Reward: 0.3157894736842105
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
O X O
O X X
X O
on move: O
O X O
O X X
X X O
Episode 153, Total Reward: 1
Average Reward: 0.3202614379084967
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 154, Total Reward: -1
Average Reward: 0.3116883116883117
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 X
O X
O O
Episode 155, Total Reward: 1
Average Reward: 0.3161290322580645
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
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 156, Total Reward: 1
Average Reward: 0.32051282051282054
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 157, Total Reward: 1
Average Reward: 0.3248407643312102
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 158, Total Reward: 1
Average Reward: 0.3291139240506329
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 159, Total Reward: 0
Average Reward: 0.3270440251572327
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
X X
X O O
X O O
on move: O
X X X
X O O
X O O
Episode 160, Total Reward: 1
Average Reward: 0.33125
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
X O X
on move: X
X X O
O O
X O X
on move: O
X X O
O X O
X O X
Episode 161, Total Reward: 1
Average Reward: 0.33540372670807456
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 O X
X X O
O O
on move: O
X O X
X X O
O O X
Episode 162, Total Reward: 1
Average Reward: 0.3395061728395062
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
O X X
X X O
on move: O
X O O
O X X
X X O
Episode 163, Total Reward: 0
Average Reward: 0.3374233128834356
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 164, Total Reward: 1
Average Reward: 0.34146341463414637
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 165, Total Reward: 1
Average Reward: 0.34545454545454546
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 O O
O X X
Episode 166, Total Reward: 0
Average Reward: 0.3433734939759036
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 167, Total Reward: -1
Average Reward: 0.33532934131736525
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 O X
X X
on move: X
O O O
X O X
X X
Episode 168, Total Reward: -1
Average Reward: 0.3273809523809524
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 169, Total Reward: 1
Average Reward: 0.33136094674556216
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
O X
X X O
Episode 170, Total Reward: -1
Average Reward: 0.3235294117647059
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 171, Total Reward: -1
Average Reward: 0.3157894736842105
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
O X X
X X O
Episode 172, Total Reward: 0
Average Reward: 0.313953488372093
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
on move: O
X O O
O X X
O X X
Episode 173, Total Reward: 1
Average Reward: 0.3179190751445087
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
Episode 174, Total Reward: 1
Average Reward: 0.3218390804597701
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
O X
X O
X X O
on move: X
O O X
X O
X X O
on move: O
O O X
X X O
X X O
Episode 175, Total Reward: 1
Average Reward: 0.32571428571428573
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 176, Total Reward: 1
Average Reward: 0.32954545454545453
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
O X
Episode 177, Total Reward: 1
Average Reward: 0.3333333333333333
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
X O X
on move: O
X X O
O X O
X O X
Episode 178, Total Reward: 1
Average Reward: 0.33707865168539325
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
X O X
O X X
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
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
on move: X
X X
O X O
O X O
on move: O
X X X
O X O
O X O
Episode 180, Total Reward: 1
Average Reward: 0.3333333333333333
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 O
X
on move: O
X O O
X X O
X
Episode 181, Total Reward: 1
Average Reward: 0.3370165745856354
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 182, Total Reward: 1
Average Reward: 0.34065934065934067
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 X
O O X
Episode 183, Total Reward: 1
Average Reward: 0.3442622950819672
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
O X
O
X O X
on move: O
O X
X O
X O X
on move: X
O O X
X O
X O X
Episode 184, Total Reward: -1
Average Reward: 0.33695652173913043
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 O
X O
O X X
Episode 185, Total Reward: -1
Average Reward: 0.32972972972972975
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
Episode 186, 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
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
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 O
X
O
on move: O
X O
X
O X
on move: X
X O
X O
O X
Episode 188, Total Reward: -1
Average Reward: 0.32978723404255317
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 X O
on move: X
X X O
O X
O X O
on move: O
X X O
O X X
O X O
Episode 189, 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
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 O X
O O
O X X
on move: O
X O X
O O X
O X X
Episode 190, Total Reward: 1
Average Reward: 0.3368421052631579
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 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 191, Total Reward: 1
Average Reward: 0.3403141361256545
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 O
X X
X X O
Episode 192, 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
X
X O
on move: O
O X
X
X O
on move: X
O X
X O
X O
Episode 193, Total Reward: -1
Average Reward: 0.32642487046632124
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 194, Total Reward: 1
Average Reward: 0.32989690721649484
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 O X
X
on move: X
O X X
O O X
X O
Episode 195, Total Reward: -1
Average Reward: 0.3230769230769231
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 X
O O
X X O
on move: X
X X O
O O
X X O
Episode 196, Total Reward: -1
Average Reward: 0.3163265306122449
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 197, Total Reward: -1
Average Reward: 0.3096446700507614
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
Episode 198, Total Reward: -1
Average Reward: 0.30303030303030304
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
O X
X O
on move: X
X O X
O X
O X O
on move: O
X O X
O X X
O X O
Episode 199, Total Reward: 0
Average Reward: 0.3015075376884422
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 200, Total Reward: 1
Average Reward: 0.305
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
O O X
X X O
Episode 201, Total Reward: 0
Average Reward: 0.3034825870646766
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 O
X O
O X O
Episode 202, Total Reward: -1
Average Reward: 0.297029702970297
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 O
X X X
Episode 203, Total Reward: 1
Average Reward: 0.30049261083743845
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
Episode 204, Total Reward: 1
Average Reward: 0.30392156862745096
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 205, Total Reward: 1
Average Reward: 0.3073170731707317
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
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 206, Total Reward: 1
Average Reward: 0.3106796116504854
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 207, Total Reward: 1
Average Reward: 0.3140096618357488
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 208, Total Reward: -1
Average Reward: 0.3076923076923077
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
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 209, Total Reward: 1
Average Reward: 0.31100478468899523
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
on move: X
O X
O O X
X X O
Episode 210, Total Reward: -1
Average Reward: 0.3047619047619048
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 211, Total Reward: -1
Average Reward: 0.2985781990521327
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
Episode 212, Total Reward: 1
Average Reward: 0.3018867924528302
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
Episode 213, Total Reward: -1
Average Reward: 0.29577464788732394
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
X O
O X X
on move: X
X O O
X O
O X X
Episode 214, Total Reward: -1
Average Reward: 0.2897196261682243
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 X
O O
X O X
on move: X
X X
O O O
X O X
Episode 215, Total Reward: -1
Average Reward: 0.2837209302325581
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
O X
X X O
on move: O
X O O
X O X
X X O
Episode 216, Total Reward: 1
Average Reward: 0.28703703703703703
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 O
X O O
on move: O
X X X
O X O
X O O
Episode 217, Total Reward: 1
Average Reward: 0.2903225806451613
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
on move: O
O X O
O X X
X O X
Episode 218, Total Reward: 0
Average Reward: 0.2889908256880734
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
O X X
O O X
on move: X
O X
O X X
O O X
Episode 219, Total Reward: -1
Average Reward: 0.2831050228310502
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 X
O X O
on move: X
X O X
O X
O X O
on move: O
X O X
O X X
O X O
Episode 220, Total Reward: 0
Average Reward: 0.2818181818181818
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 X O
X X
on move: X
O X
O X O
O X X
Episode 221, Total Reward: -1
Average Reward: 0.27601809954751133
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 O
X X O
Episode 222, Total Reward: -1
Average Reward: 0.2702702702702703
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 X O
X
on move: X
X O X
O X O
X O
on move: O
X O X
O X O
X X O
Episode 223, Total Reward: 1
Average Reward: 0.273542600896861
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
X O 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 224, Total Reward: 0
Average Reward: 0.27232142857142855
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 O
X X O
X O X
on move: O
O O X
X X O
X O X
Episode 225, Total Reward: 1
Average Reward: 0.27555555555555555
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 226, Total Reward: 1
Average Reward: 0.27876106194690264
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 O X
O O X
X O
Episode 227, Total Reward: -1
Average Reward: 0.27312775330396477
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 228, Total Reward: 1
Average Reward: 0.27631578947368424
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
O X X
on move: X
X O
O O X
O X X
Episode 229, Total Reward: -1
Average Reward: 0.27074235807860264
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 O
X X O
Episode 230, Total Reward: -1
Average Reward: 0.26521739130434785
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 O
X X
on move: X
O O X
X O O
X X
on move: O
O O X
X O O
X X X
Episode 231, Total Reward: 1
Average Reward: 0.2683982683982684
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
X O X
X X O
O O X
Episode 232, Total Reward: 1
Average Reward: 0.27155172413793105
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
Episode 233, Total Reward: 1
Average Reward: 0.27467811158798283
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 234, Total Reward: 1
Average Reward: 0.2777777777777778
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
O X X
on move: O
X O O
X X O
O X X
Episode 235, Total Reward: 1
Average Reward: 0.28085106382978725
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 X
X O
Episode 236, Total Reward: -1
Average Reward: 0.2754237288135593
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
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 237, Total Reward: 1
Average Reward: 0.27848101265822783
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 238, Total Reward: -1
Average Reward: 0.27310924369747897
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 X X
X O
on move: O
X O O
O X X
X O X
Episode 239, Total Reward: 1
Average Reward: 0.27615062761506276
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
O X
on move: X
O X X
X O
O O X
on move: O
O X X
X O X
O O X
Episode 240, Total Reward: 1
Average Reward: 0.2791666666666667
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 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 241, Total Reward: 1
Average Reward: 0.2821576763485477
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 X
O O
X O X
on move: X
X X
O O O
X O X
Episode 242, Total Reward: -1
Average Reward: 0.2768595041322314
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
Episode 243, Total Reward: -1
Average Reward: 0.2716049382716049
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 X O
X O
on move: X
X X
O X O
X O O
on move: O
X X X
O X O
X O O
Episode 244, Total Reward: 1
Average Reward: 0.27459016393442626
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 X
O X O
X
on move: X
O X X
O X O
O X
Episode 245, Total Reward: -1
Average Reward: 0.2693877551020408
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 246, Total Reward: 1
Average Reward: 0.27235772357723576
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
X X
X O X
O O O
Episode 247, Total Reward: -1
Average Reward: 0.26720647773279355
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 X O
on move: O
X X X
O O X
O X O
Episode 248, Total Reward: 1
Average Reward: 0.2701612903225806
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 249, Total Reward: 1
Average Reward: 0.27309236947791166
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 250, Total Reward: -1
Average Reward: 0.268
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 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 251, Total Reward: 0
Average Reward: 0.26693227091633465
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
X O
X O
X X O
Episode 252, Total Reward: 1
Average Reward: 0.2698412698412698
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
Episode 253, 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
Episode 254, Total Reward: 1
Average Reward: 0.2755905511811024
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
on move: X
X O O
X O X
O X
Episode 255, Total Reward: -1
Average Reward: 0.27058823529411763
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
X O O
on move: O
O X X
X X O
X O O
Episode 256, Total Reward: 1
Average Reward: 0.2734375
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
on move: X
X O X
X O O
X O
on move: O
X O X
X O O
X X O
Episode 257, Total Reward: 1
Average Reward: 0.27626459143968873
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
X X O
O X O
on move: O
X O X
X X O
O X O
Episode 258, Total Reward: 0
Average Reward: 0.2751937984496124
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 259, Total Reward: 1
Average Reward: 0.277992277992278
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 260, Total Reward: 1
Average Reward: 0.28076923076923077
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 O
X X
on move: O
O O X
X O O
X X X
Episode 261, Total Reward: 1
Average Reward: 0.2835249042145594
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 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 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
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 O
X X O
X O
on move: O
O X O
X X O
X O X
Episode 263, Total Reward: 0
Average Reward: 0.28517110266159695
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 264, Total Reward: 1
Average Reward: 0.2878787878787879
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
on move: X
X O X
O O
O X X
on move: O
X O X
O O X
O X X
Episode 265, Total Reward: 1
Average Reward: 0.29056603773584905
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 O
X X
Episode 266, Total Reward: 1
Average Reward: 0.2932330827067669
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 267, Total Reward: -1
Average Reward: 0.2883895131086142
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 268, Total Reward: -1
Average Reward: 0.2835820895522388
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 269, Total Reward: -1
Average Reward: 0.2788104089219331
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 O X
on move: X
O X O
X O
X O X
on move: O
O X O
X X O
X O X
Episode 270, Total Reward: 0
Average Reward: 0.2777777777777778
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
Episode 271, Total Reward: -1
Average Reward: 0.2730627306273063
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
X X
X O X
O O O
Episode 272, Total Reward: -1
Average Reward: 0.26838235294117646
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 273, Total Reward: 1
Average Reward: 0.27106227106227104
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
O X
on move: X
O X X
X O
O O X
on move: O
O X X
X O X
O O X
Episode 274, Total Reward: 1
Average Reward: 0.2737226277372263
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 O
O X X
X O O
Episode 275, Total Reward: 0
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 276, Total Reward: 1
Average Reward: 0.2753623188405797
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
on move: X
X O O
X O X
O X
Episode 277, Total Reward: -1
Average Reward: 0.27075812274368233
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 278, Total Reward: 1
Average Reward: 0.2733812949640288
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
Episode 279, Total Reward: 1
Average Reward: 0.27598566308243727
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 280, Total Reward: 1
Average Reward: 0.2785714285714286
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
O X X
on move: X
O X X
O O
O X X
Episode 281, Total Reward: -1
Average Reward: 0.27402135231316727
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
X O X
X O X
O O
Episode 282, Total Reward: -1
Average Reward: 0.2695035460992908
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 O
O X X
O X
Episode 283, Total Reward: 1
Average Reward: 0.27208480565371024
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 X O
X O
Episode 284, Total Reward: -1
Average Reward: 0.2676056338028169
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
O 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 285, Total Reward: 1
Average Reward: 0.27017543859649124
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
X O X
X O X
on move: O
O X O
X O X
X O X
Episode 286, Total Reward: 0
Average Reward: 0.2692307692307692
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 287, Total Reward: 1
Average Reward: 0.27177700348432055
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
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 288, Total Reward: 0
Average Reward: 0.2708333333333333
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
Episode 289, Total Reward: -1
Average Reward: 0.2664359861591695
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
O X X
O O
on move: O
X X O
O X X
O O X
Episode 290, Total Reward: 1
Average Reward: 0.2689655172413793
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 X X
O O
on move: O
X O X
O X X
X O O
Episode 291, Total Reward: 1
Average Reward: 0.27147766323024053
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 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
X O O
Episode 292, Total Reward: 1
Average Reward: 0.273972602739726
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
X O X
X X
O O
on move: X
X O X
X X
O O O
Episode 293, Total Reward: -1
Average Reward: 0.2696245733788396
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 X
O O
O X
Episode 294, Total Reward: 1
Average Reward: 0.272108843537415
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
Episode 295, Total Reward: 1
Average Reward: 0.2745762711864407
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 296, Total Reward: 1
Average Reward: 0.27702702702702703
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
on move: X
X O
O X O
X O X
on move: O
X X O
O X O
X O X
Episode 297, Total Reward: 1
Average Reward: 0.27946127946127947
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 298, Total Reward: 1
Average Reward: 0.28187919463087246
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
Episode 299, Total Reward: 1
Average Reward: 0.2842809364548495
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 300, Total Reward: -1
Average Reward: 0.28
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 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 301, Total Reward: 1
Average Reward: 0.2823920265780731
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 O
X X
Episode 302, Total Reward: -1
Average Reward: 0.2781456953642384
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 X O
X X O
on move: X
O O
X X O
X X O
on move: O
O O X
X X O
X X O
Episode 303, Total Reward: 1
Average Reward: 0.28052805280528054
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
O X
O X
on move: X
O X X
O X O
O X
on move: O
O X X
O X O
X O X
Episode 304, Total Reward: 1
Average Reward: 0.28289473684210525
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 X
O X X
Episode 305, Total Reward: 1
Average Reward: 0.28524590163934427
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 O X
O O X
O X X
Episode 306, Total Reward: 1
Average Reward: 0.2875816993464052
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
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 307, Total Reward: 1
Average Reward: 0.2899022801302932
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 X
O O O
X X O
Episode 308, 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 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 309, Total Reward: 1
Average Reward: 0.28802588996763756
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
X O
X X O
O X
Episode 310, Total Reward: 1
Average Reward: 0.2903225806451613
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 O
X X X
Episode 311, Total Reward: 1
Average Reward: 0.29260450160771706
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 312, Total Reward: 1
Average Reward: 0.2948717948717949
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 O X
X X O
Episode 313, Total Reward: 0
Average Reward: 0.2939297124600639
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
on move: X
O X O
X O
O X X
Episode 314, Total Reward: -1
Average Reward: 0.2898089171974522
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 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 315, Total Reward: 0
Average Reward: 0.28888888888888886
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 316, Total Reward: 1
Average Reward: 0.2911392405063291
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
O X
X O
X X O
on move: X
O X O
X O
X X O
Episode 317, Total Reward: -1
Average Reward: 0.2870662460567823
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
Episode 318, Total Reward: 1
Average Reward: 0.2893081761006289
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
on move: X
O X
O O X
O X X
Episode 319, Total Reward: -1
Average Reward: 0.2852664576802508
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
O X X
X O
X O
on move: X
O X X
X O O
X O
Episode 320, Total Reward: -1
Average Reward: 0.28125
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
Episode 321, Total Reward: -1
Average Reward: 0.2772585669781931
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 X
O O X
Episode 322, Total Reward: 1
Average Reward: 0.2795031055900621
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
O X O
X X O
X
on move: X
O X O
X X O
X O
Episode 323, Total Reward: -1
Average Reward: 0.2755417956656347
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
Episode 324, Total Reward: 1
Average Reward: 0.2777777777777778
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
Episode 325, Total Reward: 1
Average Reward: 0.28
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
X X O
O X O
on move: O
X O X
X X O
O X O
Episode 326, Total Reward: 0
Average Reward: 0.2791411042944785
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
X O
X X
X O O
Episode 327, Total Reward: 1
Average Reward: 0.28134556574923547
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
Episode 328, Total Reward: -1
Average Reward: 0.2774390243902439
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
O X X
on move: X
O O O
X X
O X X
Episode 329, Total Reward: -1
Average Reward: 0.2735562310030395
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
X
O X O
O X X
Episode 330, Total Reward: 1
Average Reward: 0.27575757575757576
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
Episode 331, Total Reward: -1
Average Reward: 0.2719033232628399
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 X
X X
O X O
on move: O
O O X
X X X
O X O
Episode 332, Total Reward: 1
Average Reward: 0.2740963855421687
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
Episode 333, Total Reward: 1
Average Reward: 0.27627627627627627
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
X O X
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 334, Total Reward: 0
Average Reward: 0.2754491017964072
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 335, Total Reward: 1
Average Reward: 0.27761194029850744
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
Episode 336, Total Reward: 1
Average Reward: 0.27976190476190477
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 O
X X X
O X O
Episode 337, Total Reward: 1
Average Reward: 0.2818991097922849
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
on move: O
X O X
X X
O O
on move: X
X O X
X X
O O O
Episode 338, Total Reward: -1
Average Reward: 0.2781065088757396
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
Episode 339, Total Reward: 1
Average Reward: 0.28023598820059
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
Episode 340, Total Reward: -1
Average Reward: 0.27647058823529413
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 341, Total Reward: -1
Average Reward: 0.2727272727272727
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
X O
O X
X X O
on move: X
X O
O O X
X X O
on move: O
X X O
O O X
X X O
Episode 342, Total Reward: 0
Average Reward: 0.2719298245614035
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
X O O
on move: X
O X X
O X
X O O
on move: O
O X X
O X X
X O O
Episode 343, Total Reward: 1
Average Reward: 0.27405247813411077
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 344, Total Reward: 1
Average Reward: 0.2761627906976744
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
Episode 345, Total Reward: 1
Average Reward: 0.2782608695652174
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 O X
Episode 346, Total Reward: 1
Average Reward: 0.28034682080924855
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 347, Total Reward: 1
Average Reward: 0.2824207492795389
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
Episode 348, Total Reward: 1
Average Reward: 0.28448275862068967
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
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 X
O O X
Episode 349, Total Reward: 1
Average Reward: 0.28653295128939826
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
Episode 350, Total Reward: 1
Average Reward: 0.2885714285714286
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
X O
X O
Episode 351, Total Reward: 1
Average Reward: 0.2905982905982906
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 352, Total Reward: 1
Average Reward: 0.29261363636363635
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
Episode 353, Total Reward: 1
Average Reward: 0.29461756373937675
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 354, Total Reward: 1
Average Reward: 0.2966101694915254
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
Episode 355, Total Reward: -1
Average Reward: 0.29295774647887324
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 356, Total Reward: 1
Average Reward: 0.2949438202247191
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 357, Total Reward: 1
Average Reward: 0.2969187675070028
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 O O
X X O
on move: X
O X
X O O
X X O
Episode 358, Total Reward: -1
Average Reward: 0.29329608938547486
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
Episode 359, Total Reward: 1
Average Reward: 0.29526462395543174
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 X O
O X X
O O
on move: O
X X O
O X X
O X O
Episode 360, Total Reward: 1
Average Reward: 0.2972222222222222
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
O X X
X O X
O O
on move: O
O X X
X O X
O O X
Episode 361, Total Reward: 1
Average Reward: 0.29916897506925205
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 O X
X X
on move: X
O O
X O X
X X O
Episode 362, Total Reward: -1
Average Reward: 0.2955801104972376
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 363, Total Reward: 1
Average Reward: 0.2975206611570248
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
X O
X O
X X O
Episode 364, Total Reward: 1
Average Reward: 0.29945054945054944
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 365, Total Reward: 0
Average Reward: 0.29863013698630136
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 X
O X O
Episode 366, Total Reward: 1
Average Reward: 0.3005464480874317
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 367, Total Reward: 1
Average Reward: 0.3024523160762943
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
O X X
Episode 368, Total Reward: -1
Average Reward: 0.29891304347826086
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 X
O O
X O X
on move: X
X X O
O O
X O X
on move: O
X X O
O X O
X O X
Episode 369, Total Reward: 1
Average Reward: 0.3008130081300813
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 370, Total Reward: -1
Average Reward: 0.2972972972972973
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
on move: X
O X O
O X O
X X
on move: O
O X O
O X O
X X X
Episode 371, Total Reward: 1
Average Reward: 0.2991913746630728
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 O X
X
on move: X
O X O
X O X
X O
Episode 372, Total Reward: -1
Average Reward: 0.2956989247311828
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
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 X
O X X
Episode 373, Total Reward: 1
Average Reward: 0.2975871313672922
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 O X
X O X
X O
Episode 374, 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 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 375, Total Reward: -1
Average Reward: 0.2906666666666667
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
Episode 376, Total Reward: 1
Average Reward: 0.2925531914893617
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 O
X O X
on move: O
O X X
X O O
X O X
Episode 377, Total Reward: 0
Average Reward: 0.2917771883289125
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
on move: X
X O O
X X O
O X
on move: O
X O O
X X O
O X X
Episode 378, Total Reward: 1
Average Reward: 0.29365079365079366
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 379, Total Reward: 1
Average Reward: 0.2955145118733509
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
Episode 380, Total Reward: 1
Average Reward: 0.29736842105263156
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 O X
O O X
X X O
Episode 381, Total Reward: 0
Average Reward: 0.29658792650918636
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
O X
X O O
O X X
on move: O
O X X
X O O
O X X
Episode 382, Total Reward: 0
Average Reward: 0.29581151832460734
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 O X
on move: X
O O O
X X
X O X
Episode 383, Total Reward: -1
Average Reward: 0.2924281984334204
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 384, Total Reward: 1
Average Reward: 0.2942708333333333
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
on move: O
X X X
O X O
O O X
Episode 385, Total Reward: 1
Average Reward: 0.2961038961038961
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 O X
X O
O X X
on move: O
O O X
X O X
O X X
Episode 386, Total Reward: 1
Average Reward: 0.2979274611398964
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 O X
O O X
X O
on move: O
X O X
O O X
X X O
Episode 387, Total Reward: 0
Average Reward: 0.2971576227390181
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
on move: X
X X O
O X
X O O
on move: O
X X O
O X X
X O O
Episode 388, Total Reward: 0
Average Reward: 0.2963917525773196
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
on move: O
O O X
O X X
X O X
Episode 389, Total Reward: 1
Average Reward: 0.2982005141388175
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
X O
X X
X O O
Episode 390, Total Reward: 1
Average Reward: 0.3
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
X O O
X X
X O
on move: X
X O O
X X O
X O
Episode 391, Total Reward: -1
Average Reward: 0.2966751918158568
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 392, Total Reward: 1
Average Reward: 0.29846938775510207
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
X O
O X O
X X
on move: X
X O
O X O
X X O
Episode 393, Total Reward: -1
Average Reward: 0.2951653944020356
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
O X O
X X O
Episode 394, Total Reward: 1
Average Reward: 0.2969543147208122
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
O X O
O X
X O X
on move: O
O X O
O X X
X O X
Episode 395, Total Reward: 0
Average Reward: 0.29620253164556964
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 396, Total Reward: 1
Average Reward: 0.29797979797979796
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 397, Total Reward: 1
Average Reward: 0.29974811083123426
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 398, Total Reward: 1
Average Reward: 0.3015075376884422
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 399, Total Reward: 1
Average Reward: 0.3032581453634085
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
X O
X O X
X O
on move: X
X O O
X O X
X O
on move: O
X O O
X O X
X X O
Episode 400, Total Reward: 1
Average Reward: 0.305