106 KiB
Крестики-нолики: https://github.com/nczempin/gym-tic-tac-toe
Перевод среды на Gymnasium
Ключевые функции Gymnasium:
env.reset() — инициализация среды.
env.step(action) — выполнение действия и переход в новое состояние.
env.render() — визуализация текущего состояния среды.
import gymnasium as gym
from gymnasium import spaces
import numpy as np
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
Роль агента:
Агент принимает решение (выбирает действие), основываясь на текущем состоянии среды, и затем получает обратную связь (награду и новое состояние) от среды.
Функционал агента:
Выбор действия: Использует алгоритмы или стратегии, чтобы определить, что делать дальше.
Обучение: Обновляет свои знания или стратегию на основе опыта, чтобы лучше справляться с задачей.
Интерактивность: Адаптируется к изменениям в среде.
import random
# Реализация Агента, который в рамках обучения с подкреплением взаимодействует со средой и вырабатывает наилучшую стратегию
class Agent:
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¶
Основной цикл включает в себя создание среды и работу с ней. По истечению выполнения игры, начисляются очки, которые будут свидетельствовать о том, какие результаты достиг наш агент, обучилась ли наша система.
# Основной цикл обучения (работа с отдельным классом агента)
# Создание среды для игры в крестики-нолики
environment = TicTacToeEnv()
# Создание агента (играющего крестиками)
agent = Agent(symbol=1)
num_episodes = 150 # Количество эпизодов (игр) для обучения
collected_rewards = [] # Список для хранения наград/побед в каждом эпизоде
# Переменная для отслеживания символа и текущего игрока
oom = 1
for i in range(num_episodes):
# Сброс среды и начало нового эпизода
state, _ = environment.reset()
# Общая награда за эпизод
total_reward = 0
# Флаг завершения игры
done = False
om = oom
# Максимум 9 ходов, поскольку поле 3x3
for j in range(9):
moves = environment.move_generator()
# Ходов нет, заканчиваем игру
if not moves:
break
if len(moves) == 1:
move = moves[0] # Если остался один ход на основе стратегии
else:
move = agent.get_action(moves) # Агент выбирает ход на основе стратегии
# Выполнение хода и обновление состояния игры
next_state, reward, done, info = environment.step(move)
total_reward += reward
state = next_state
# Отображаем текущее состояние игры
environment.render()
if done:
break
om = -om # Смена игрока
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 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 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 1, Total Reward: 1 Average Reward: 1.0 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 X O X 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 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 3, 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 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 4, Total Reward: -1 Average Reward: 0.5 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 O X X on move: O O O X X O O X X X Episode 5, Total Reward: 1 Average Reward: 0.6 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 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 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 O X X O Episode 7, 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 O X O on move: O X O X X O Episode 8, 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 O X O X on move: X X O O X O X on move: O X O O X X O X 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 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 Episode 10, Total Reward: 1 Average Reward: 0.8 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 11, Total Reward: -1 Average Reward: 0.6363636363636364 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 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 12, Total Reward: 1 Average Reward: 0.6666666666666666 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 on move: X O X O X X O O X on move: O O X O X X X O O X 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 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 O X O on move: O X O X X X O O X O Episode 14, Total Reward: 0 Average Reward: 0.6428571428571429 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 X O on move: O X O X O O X X X O Episode 15, Total Reward: 0 Average Reward: 0.6 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 16, Total Reward: -1 Average Reward: 0.5 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 17, Total Reward: 1 Average Reward: 0.5294117647058824 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 18, Total Reward: -1 Average Reward: 0.4444444444444444 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 19, Total Reward: -1 Average Reward: 0.3684210526315789 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 20, Total Reward: -1 Average Reward: 0.3 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 21, 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 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 22, Total Reward: 1 Average Reward: 0.36363636363636365 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 O X O X O X on move: O X O X O X O X Episode 23, Total Reward: 1 Average Reward: 0.391304347826087 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 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 24, Total Reward: 0 Average Reward: 0.375 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 25, Total Reward: 1 Average Reward: 0.4 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 26, Total Reward: 0 Average Reward: 0.38461538461538464 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 27, Total Reward: 1 Average Reward: 0.4074074074074074 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 28, Total Reward: -1 Average Reward: 0.35714285714285715 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 X X O X X O O O on move: O X X O X X O O O X Episode 29, Total Reward: 1 Average Reward: 0.3793103448275862 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 X O O X X O Episode 30, Total Reward: 1 Average Reward: 0.4 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 O X on move: O O X X O X O X on move: X O X X O X O X O Episode 31, Total Reward: -1 Average Reward: 0.3548387096774194 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 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 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 O X X X O on move: O O X O O X X X X O Episode 33, 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 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 O O X X Episode 34, Total Reward: 1 Average Reward: 0.35294117647058826 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 35, Total Reward: 1 Average Reward: 0.37142857142857144 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 X O O X O Episode 36, Total Reward: 1 Average Reward: 0.3888888888888889 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 37, Total Reward: 1 Average Reward: 0.40540540540540543 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 38, Total Reward: 1 Average Reward: 0.42105263157894735 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 O X on move: O O X O X X O X Episode 39, Total Reward: 1 Average Reward: 0.4358974358974359 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 40, Total Reward: 1 Average Reward: 0.45 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 41, Total Reward: -1 Average Reward: 0.4146341463414634 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 42, Total Reward: 1 Average Reward: 0.42857142857142855 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 X O Episode 43, Total Reward: -1 Average Reward: 0.3953488372093023 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 X X X O O X O on move: O X O X X X O O X O Episode 44, Total Reward: 0 Average Reward: 0.38636363636363635 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 45, Total Reward: -1 Average Reward: 0.35555555555555557 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 46, Total Reward: -1 Average Reward: 0.32608695652173914 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 47, Total Reward: 1 Average Reward: 0.3404255319148936 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 48, Total Reward: 1 Average Reward: 0.3541666666666667 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 O X X X O O on move: O X O X O X X X O O Episode 49, Total Reward: 1 Average Reward: 0.3673469387755102 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 Episode 50, Total Reward: -1 Average Reward: 0.34 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 51, Total Reward: 1 Average Reward: 0.35294117647058826 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 52, Total Reward: 1 Average Reward: 0.36538461538461536 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 53, Total Reward: 1 Average Reward: 0.37735849056603776 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 O X 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 54, Total Reward: 0 Average Reward: 0.37037037037037035 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 O X O on move: O X X X O O X O X O Episode 55, Total Reward: 1 Average Reward: 0.38181818181818183 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 O X X O O X X O Episode 56, Total Reward: -1 Average Reward: 0.35714285714285715 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 57, Total Reward: 1 Average Reward: 0.3684210526315789 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 58, Total Reward: -1 Average Reward: 0.3448275862068966 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 59, Total Reward: -1 Average Reward: 0.3220338983050847 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 60, 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 on move: O X X X X O O O Episode 61, 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 O X X Episode 62, 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 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 O X O O Episode 63, 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 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 X O O X O Episode 64, Total Reward: 0 Average Reward: 0.328125 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 Episode 65, Total Reward: 1 Average Reward: 0.3384615384615385 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 O X X X O X O X Episode 66, Total Reward: 1 Average Reward: 0.3484848484848485 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 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 67, Total Reward: 1 Average Reward: 0.3582089552238806 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 O X on move: O O X O O X X X O X Episode 68, Total Reward: 0 Average Reward: 0.35294117647058826 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 O X on move: O X O X X O O O X X Episode 69, Total Reward: 0 Average Reward: 0.34782608695652173 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 70, Total Reward: -1 Average Reward: 0.32857142857142857 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 71, Total Reward: 1 Average Reward: 0.3380281690140845 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 on move: X X O O X X O X O on move: O X O O X X X O X O Episode 72, Total Reward: 1 Average Reward: 0.3472222222222222 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 Episode 73, Total Reward: -1 Average Reward: 0.3287671232876712 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 Episode 74, Total Reward: -1 Average Reward: 0.3108108108108108 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 O X X O O X X on move: O O X O X X O O X X Episode 75, 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 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 X O X Episode 76, Total Reward: 0 Average Reward: 0.3157894736842105 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 77, Total Reward: 1 Average Reward: 0.3246753246753247 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 Episode 78, 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 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 79, Total Reward: -1 Average Reward: 0.31645569620253167 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 X X O O on move: O O X X O X X X O O Episode 80, Total Reward: 1 Average Reward: 0.325 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 81, 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 on move: X O O O X X X O X on move: O O X O O X X X O X Episode 82, Total Reward: 0 Average Reward: 0.32926829268292684 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 83, Total Reward: 1 Average Reward: 0.3373493975903614 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 Episode 84, Total Reward: -1 Average Reward: 0.32142857142857145 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 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 85, Total Reward: 0 Average Reward: 0.3176470588235294 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 86, Total Reward: 1 Average Reward: 0.32558139534883723 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 on move: O X X O X O O X O X Episode 87, 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 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 O X O O O X X on move: O X O X O O X O X X Episode 88, Total Reward: 1 Average Reward: 0.3409090909090909 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 on move: X X O X O X O X O on move: O X O X X O X O X O Episode 89, Total Reward: 0 Average Reward: 0.33707865168539325 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 X O O X O X X Episode 90, Total Reward: 1 Average Reward: 0.34444444444444444 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 X O X 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 91, Total Reward: 0 Average Reward: 0.34065934065934067 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 92, Total Reward: -1 Average Reward: 0.32608695652173914 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 93, 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 Episode 94, Total Reward: 1 Average Reward: 0.3404255319148936 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 O X O O O X Episode 95, Total Reward: -1 Average Reward: 0.3263157894736842 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 96, 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 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 97, Total Reward: 1 Average Reward: 0.31958762886597936 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 Episode 98, Total Reward: -1 Average Reward: 0.30612244897959184 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 O X X on move: X O O O X X O X X Episode 99, Total Reward: -1 Average Reward: 0.29292929292929293 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 Episode 100, 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 X O O on move: X X X X O O O on move: O X X X X O O O Episode 101, Total Reward: 1 Average Reward: 0.3069306930693069 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 102, Total Reward: -1 Average Reward: 0.29411764705882354 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 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 103, Total Reward: 1 Average Reward: 0.30097087378640774 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 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 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 X O X X X O O O X Episode 106, Total Reward: 1 Average Reward: 0.32075471698113206 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 X O X X Episode 107, Total Reward: -1 Average Reward: 0.308411214953271 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 108, Total Reward: 1 Average Reward: 0.3148148148148148 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 Episode 109, Total Reward: 1 Average Reward: 0.3211009174311927 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 110, Total Reward: 1 Average Reward: 0.32727272727272727 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 Episode 111, 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 X O O X Episode 112, Total Reward: 1 Average Reward: 0.3392857142857143 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 O X X X O O O X on move: O O X X X X O O O X Episode 113, Total Reward: 0 Average Reward: 0.336283185840708 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 114, Total Reward: 1 Average Reward: 0.34210526315789475 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 O O X X O X Episode 115, Total Reward: 0 Average Reward: 0.3391304347826087 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 Episode 116, Total Reward: 1 Average Reward: 0.3448275862068966 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 117, 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 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 O X O X O X Episode 118, Total Reward: 1 Average Reward: 0.3389830508474576 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 119, Total Reward: 0 Average Reward: 0.33613445378151263 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 O X O X O X on move: O O X O X O X X O X Episode 120, 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 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 Episode 121, Total Reward: 1 Average Reward: 0.33884297520661155 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 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 122, 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 X O O X Episode 123, Total Reward: 1 Average Reward: 0.34959349593495936 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 124, Total Reward: 1 Average Reward: 0.3548387096774194 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 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 125, Total Reward: 1 Average Reward: 0.36 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 126, Total Reward: 1 Average Reward: 0.36507936507936506 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 127, Total Reward: 1 Average Reward: 0.3700787401574803 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 128, Total Reward: -1 Average Reward: 0.359375 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 129, Total Reward: 1 Average Reward: 0.3643410852713178 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 O X O O Episode 130, Total Reward: -1 Average Reward: 0.35384615384615387 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 131, Total Reward: 1 Average Reward: 0.35877862595419846 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 Episode 132, Total Reward: 1 Average Reward: 0.36363636363636365 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 Episode 133, Total Reward: 1 Average Reward: 0.3684210526315789 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 O X X O O X on move: O O X O X X X O O X Episode 134, Total Reward: 1 Average Reward: 0.373134328358209 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 on move: X O X O X X O X O on move: O O X O X X O X O X Episode 135, Total Reward: 0 Average Reward: 0.37037037037037035 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 136, Total Reward: 1 Average Reward: 0.375 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 O X O on move: O X X O O X O X O X Episode 137, Total Reward: 1 Average Reward: 0.3795620437956204 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 on move: X X O O X X O X O on move: O X O O X X X O X O Episode 138, Total Reward: 1 Average Reward: 0.38405797101449274 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 O X X O O Episode 139, Total Reward: -1 Average Reward: 0.37410071942446044 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 O X X O on move: O X X O O O X X X O Episode 140, Total Reward: 0 Average Reward: 0.37142857142857144 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 141, Total Reward: 1 Average Reward: 0.375886524822695 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 O X X O on move: X O X X O X X O O Episode 142, Total Reward: -1 Average Reward: 0.36619718309859156 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 O X O X X Episode 143, Total Reward: -1 Average Reward: 0.35664335664335667 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 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 X O Episode 144, Total Reward: 0 Average Reward: 0.3541666666666667 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 145, Total Reward: 1 Average Reward: 0.3586206896551724 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 146, Total Reward: 1 Average Reward: 0.363013698630137 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 O X O O X on move: O O X X O X O X O X Episode 147, Total Reward: 1 Average Reward: 0.3673469387755102 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 148, Total Reward: 1 Average Reward: 0.3716216216216216 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 Episode 149, Total Reward: 1 Average Reward: 0.37583892617449666 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 O O X Episode 150, Total Reward: 1 Average Reward: 0.38