5046 lines
106 KiB
Plaintext
Raw Normal View History

2024-12-19 21:24:58 +04:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Крестики-нолики: https://github.com/nczempin/gym-tic-tac-toe"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Перевод среды на Gymnasium \n",
"\n",
"*Ключевые функции Gymnasium:* \n",
"env.reset() — инициализация среды. \n",
"env.step(action) — выполнение действия и переход в новое состояние. \n",
"env.render() — визуализация текущего состояния среды. "
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"import gymnasium as gym\n",
"from gymnasium import spaces\n",
"import numpy as np\n",
"\n",
"class TicTacToeEnv(gym.Env):\n",
" metadata = {'render.modes': ['human']}\n",
" \n",
" symbols = ['O', ' ', 'X']\n",
"\n",
" def __init__(self):\n",
" super().__init__()\n",
" self.action_space = spaces.Discrete(9)\n",
" self.observation_space = spaces.Discrete(9 * 3 * 2)\n",
" self.reset()\n",
"\n",
" def step(self, action):\n",
" done = False\n",
" reward = 0\n",
"\n",
" p, square = action # p - игрок (1 или -1), square - номер клетки\n",
"\n",
" board = self.state['board']\n",
" proposed = board[square] \n",
" om = self.state['on_move'] \n",
" if proposed != 0: # Клетка уже занята\n",
" print(f\"Незаконный ход: Квадрат {square} уже занят.\")\n",
" done = True\n",
" reward = -1 * om \n",
" if p != om: # Не тот игрок на ходу\n",
" print(f\"Незаконный ход: игрок {p} не находится в движении\")\n",
" done = True\n",
" reward = -1 * om\n",
" else:\n",
" board[square] = p\n",
" self.state['on_move'] = -p\n",
"\n",
" for i in range(3):\n",
" # Горизонтали и вертикали\n",
" if (board[i * 3] == p and board[i * 3 + 1] == p and board[i * 3 + 2] == p) or \\\n",
" (board[i] == p and board[i + 3] == p and board[i + 6] == p):\n",
" reward = p\n",
" done = True\n",
" break\n",
"\n",
" # Диагонали\n",
" if (board[0] == p and board[4] == p and board[8] == p) or \\\n",
" (board[2] == p and board[4] == p and board[6] == p):\n",
" reward = p\n",
" done = True\n",
" \n",
" return self.state, reward, done, {}\n",
"\n",
" def reset(self):\n",
" self.state = {}\n",
" self.state['board'] = [0, 0, 0, 0, 0, 0, 0, 0, 0] \n",
" self.state['on_move'] = 1 \n",
" return self.state, {}\n",
"\n",
" def render(self, close=False):\n",
" if close:\n",
" return\n",
" print(\"on move: \" , self.symbols[self.state['on_move']+1])\n",
" for i in range (9):\n",
" print (self.symbols[self.state['board'][i]+1], end=\" \");\n",
" if ((i % 3) == 2):\n",
" print();\n",
"\n",
" def move_generator(self):\n",
" moves = []\n",
" for i in range(9):\n",
" if self.state['board'][i] == 0:\n",
" p = self.state['on_move']\n",
" m = [p, i]\n",
" moves.append(m)\n",
" return moves"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Реализация агента \n",
"\n",
"Роль агента: \n",
"Агент принимает решение (выбирает действие), основываясь на текущем состоянии среды, и затем получает обратную связь (награду и новое состояние) от среды. \n",
"\n",
"Функционал агента: \n",
"Выбор действия: Использует алгоритмы или стратегии, чтобы определить, что делать дальше. \n",
"Обучение: Обновляет свои знания или стратегию на основе опыта, чтобы лучше справляться с задачей. \n",
"Интерактивность: Адаптируется к изменениям в среде. "
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"import random\n",
"\n",
"# Реализация Агента, который в рамках обучения с подкреплением взаимодействует со средой и вырабатывает наилучшую стратегию \n",
"\n",
"class Agent:\n",
" def __init__(self, symbol):\n",
" self.symbol = symbol # Символ игрока (1 - X, -1 - O)\n",
" \n",
" def get_action(self, moves):\n",
" return random.choice(moves) # Выбираем случайный ход из доступных"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Основной цикл обучения \n",
"\n",
"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. "
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" \n",
"O X \n",
"on move: O\n",
" \n",
" \n",
"O X X \n",
"on move: X\n",
" \n",
" O \n",
"O X X \n",
"on move: O\n",
" \n",
" X O \n",
"O X X \n",
"on move: X\n",
" O \n",
" X O \n",
"O X X \n",
"on move: O\n",
" O \n",
"X X O \n",
"O X X \n",
"on move: X\n",
"O O \n",
"X X O \n",
"O X X \n",
"on move: O\n",
"O X O \n",
"X X O \n",
"O X X \n",
"Episode 1, Total Reward: 1\n",
"Average Reward: 1.0\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" \n",
" O X \n",
"on move: O\n",
" \n",
"X \n",
" O X \n",
"on move: X\n",
" O \n",
"X \n",
" O X \n",
"on move: O\n",
" O \n",
"X X \n",
" O X \n",
"on move: X\n",
" O O \n",
"X X \n",
" O X \n",
"on move: O\n",
" O O \n",
"X X X \n",
" O X \n",
"Episode 2, Total Reward: 1\n",
"Average Reward: 1.0\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" \n",
" O \n",
"on move: O\n",
"X \n",
"X \n",
" O \n",
"on move: X\n",
"X O \n",
"X \n",
" O \n",
"on move: O\n",
"X O \n",
"X X \n",
" O \n",
"on move: X\n",
"X O \n",
"X X \n",
" O O \n",
"on move: O\n",
"X O \n",
"X X \n",
"X O O \n",
"Episode 3, Total Reward: 1\n",
"Average Reward: 1.0\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" O \n",
"X \n",
" \n",
"on move: O\n",
" O \n",
"X \n",
" X \n",
"on move: X\n",
" O \n",
"X O \n",
" X \n",
"on move: O\n",
" O \n",
"X X O \n",
" X \n",
"on move: X\n",
"O O \n",
"X X O \n",
" X \n",
"on move: O\n",
"O O \n",
"X X O \n",
"X X \n",
"on move: X\n",
"O O O \n",
"X X O \n",
"X X \n",
"Episode 4, Total Reward: -1\n",
"Average Reward: 0.5\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" O \n",
" \n",
" X X \n",
"on move: X\n",
" O \n",
" O \n",
" X X \n",
"on move: O\n",
" O X \n",
" O \n",
" X X \n",
"on move: X\n",
"O O X \n",
" O \n",
" X X \n",
"on move: O\n",
"O O X \n",
"X O \n",
" X X \n",
"on move: X\n",
"O O X \n",
"X O O \n",
" X X \n",
"on move: O\n",
"O O X \n",
"X O O \n",
"X X X \n",
"Episode 5, Total Reward: 1\n",
"Average Reward: 0.6\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X O \n",
" \n",
"on move: O\n",
"X \n",
"X O \n",
" \n",
"on move: X\n",
"X \n",
"X O \n",
" O \n",
"on move: O\n",
"X \n",
"X O \n",
"X O \n",
"Episode 6, Total Reward: 1\n",
"Average Reward: 0.6666666666666666\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" O \n",
" X \n",
" \n",
"on move: O\n",
" O X \n",
" X \n",
" \n",
"on move: X\n",
" O X \n",
"O X \n",
" \n",
"on move: O\n",
"X O X \n",
"O X \n",
" \n",
"on move: X\n",
"X O X \n",
"O X \n",
" O \n",
"on move: O\n",
"X O X \n",
"O X \n",
"X O \n",
"Episode 7, Total Reward: 1\n",
"Average Reward: 0.7142857142857143\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
" X \n",
"O X \n",
" O \n",
"on move: O\n",
" X \n",
"O X \n",
"X O \n",
"Episode 8, Total Reward: 1\n",
"Average Reward: 0.75\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" \n",
" O \n",
"on move: O\n",
"X \n",
" \n",
" O X \n",
"on move: X\n",
"X O \n",
" \n",
" O X \n",
"on move: O\n",
"X O \n",
"X \n",
" O X \n",
"on move: X\n",
"X O O \n",
"X \n",
" O X \n",
"on move: O\n",
"X O O \n",
"X \n",
"X O X \n",
"Episode 9, Total Reward: 1\n",
"Average Reward: 0.7777777777777778\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
"O \n",
"on move: O\n",
" \n",
" X X \n",
"O \n",
"on move: X\n",
" O \n",
" X X \n",
"O \n",
"on move: O\n",
"X O \n",
" X X \n",
"O \n",
"on move: X\n",
"X O \n",
"O X X \n",
"O \n",
"on move: O\n",
"X O \n",
"O X X \n",
"O X \n",
"Episode 10, Total Reward: 1\n",
"Average Reward: 0.8\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
" O \n",
"on move: O\n",
" X X \n",
" \n",
" O \n",
"on move: X\n",
" X X \n",
" O \n",
" O \n",
"on move: O\n",
" X X \n",
" X O \n",
" O \n",
"on move: X\n",
" X X \n",
" X O \n",
" O O \n",
"on move: O\n",
" X X \n",
"X X O \n",
" O O \n",
"on move: X\n",
" X X \n",
"X X O \n",
"O O O \n",
"Episode 11, Total Reward: -1\n",
"Average Reward: 0.6363636363636364\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" O X \n",
" \n",
" \n",
"on move: O\n",
" O X \n",
" X \n",
" \n",
"on move: X\n",
" O X \n",
"O X \n",
" \n",
"on move: O\n",
"X O X \n",
"O X \n",
" \n",
"on move: X\n",
"X O X \n",
"O X \n",
" O \n",
"on move: O\n",
"X O X \n",
"O X X \n",
" O \n",
"on move: X\n",
"X O X \n",
"O X X \n",
"O O \n",
"on move: O\n",
"X O X \n",
"O X X \n",
"O O X \n",
"Episode 12, Total Reward: 1\n",
"Average Reward: 0.6666666666666666\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" X O \n",
" \n",
" X \n",
"on move: X\n",
" X O \n",
" \n",
" O X \n",
"on move: O\n",
" X O \n",
" X \n",
" O X \n",
"on move: X\n",
"O X O \n",
" X \n",
" O X \n",
"on move: O\n",
"O X O \n",
" X X \n",
" O X \n",
"on move: X\n",
"O X O \n",
" X X \n",
"O O X \n",
"on move: O\n",
"O X O \n",
"X X X \n",
"O O X \n",
"Episode 13, Total Reward: 1\n",
"Average Reward: 0.6923076923076923\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
" O \n",
"on move: O\n",
" \n",
"X \n",
" X O \n",
"on move: X\n",
" O \n",
"X \n",
" X O \n",
"on move: O\n",
" O \n",
"X X \n",
" X O \n",
"on move: X\n",
" O \n",
"X X O \n",
" X O \n",
"on move: O\n",
" O X \n",
"X X O \n",
" X O \n",
"on move: X\n",
" O X \n",
"X X O \n",
"O X O \n",
"on move: O\n",
"X O X \n",
"X X O \n",
"O X O \n",
"Episode 14, Total Reward: 0\n",
"Average Reward: 0.6428571428571429\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
"O \n",
" \n",
"on move: O\n",
"X X \n",
"O \n",
" \n",
"on move: X\n",
"X X \n",
"O O \n",
" \n",
"on move: O\n",
"X X \n",
"O O \n",
" X \n",
"on move: X\n",
"X O X \n",
"O O \n",
" X \n",
"on move: O\n",
"X O X \n",
"O O \n",
"X X \n",
"on move: X\n",
"X O X \n",
"O O \n",
"X X O \n",
"on move: O\n",
"X O X \n",
"O O X \n",
"X X O \n",
"Episode 15, Total Reward: 0\n",
"Average Reward: 0.6\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" \n",
"X O \n",
"on move: O\n",
" X \n",
" \n",
"X O \n",
"on move: X\n",
" X \n",
" O \n",
"X O \n",
"on move: O\n",
" X \n",
" O X \n",
"X O \n",
"on move: X\n",
" X \n",
"O O X \n",
"X O \n",
"on move: O\n",
" X \n",
"O O X \n",
"X X O \n",
"on move: X\n",
"O X \n",
"O O X \n",
"X X O \n",
"Episode 16, Total Reward: -1\n",
"Average Reward: 0.5\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X \n",
" X O \n",
" \n",
"on move: X\n",
"O X \n",
" X O \n",
" \n",
"on move: O\n",
"O X \n",
" X O \n",
" X \n",
"Episode 17, Total Reward: 1\n",
"Average Reward: 0.5294117647058824\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" O \n",
" X \n",
"on move: O\n",
" X \n",
" O \n",
" X \n",
"on move: X\n",
" X \n",
"O O \n",
" X \n",
"on move: O\n",
" X \n",
"O O \n",
" X X \n",
"on move: X\n",
" X \n",
"O O \n",
"O X X \n",
"on move: O\n",
"X X \n",
"O O \n",
"O X X \n",
"on move: X\n",
"X X \n",
"O O O \n",
"O X X \n",
"Episode 18, Total Reward: -1\n",
"Average Reward: 0.4444444444444444\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
" X \n",
" O X \n",
" O \n",
"on move: O\n",
"X X \n",
" O X \n",
" O \n",
"on move: X\n",
"X O X \n",
" O X \n",
" O \n",
"Episode 19, Total Reward: -1\n",
"Average Reward: 0.3684210526315789\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
"O \n",
"on move: O\n",
" \n",
"X X \n",
"O \n",
"on move: X\n",
" \n",
"X X \n",
"O O \n",
"on move: O\n",
" X \n",
"X X \n",
"O O \n",
"on move: X\n",
" O X \n",
"X X \n",
"O O \n",
"on move: O\n",
"X O X \n",
"X X \n",
"O O \n",
"on move: X\n",
"X O X \n",
"X X \n",
"O O O \n",
"Episode 20, Total Reward: -1\n",
"Average Reward: 0.3\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
"O \n",
"on move: O\n",
" X \n",
" \n",
"O X \n",
"on move: X\n",
" X \n",
" \n",
"O O X \n",
"on move: O\n",
"X X \n",
" \n",
"O O X \n",
"on move: X\n",
"X X \n",
"O \n",
"O O X \n",
"on move: O\n",
"X X \n",
"O X \n",
"O O X \n",
"Episode 21, Total Reward: 1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
"O \n",
" X \n",
" \n",
"on move: O\n",
"O \n",
" X \n",
"X \n",
"on move: X\n",
"O \n",
" X O \n",
"X \n",
"on move: O\n",
"O \n",
" X O \n",
"X X \n",
"on move: X\n",
"O \n",
" X O \n",
"X X O \n",
"on move: O\n",
"O X \n",
" X O \n",
"X X O \n",
"Episode 22, Total Reward: 1\n",
"Average Reward: 0.36363636363636365\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X O \n",
" \n",
"on move: O\n",
" \n",
"X O \n",
"X \n",
"on move: X\n",
" \n",
"X O \n",
"X O \n",
"on move: O\n",
" \n",
"X O \n",
"X O X \n",
"on move: X\n",
" O \n",
"X O \n",
"X O X \n",
"on move: O\n",
"X O \n",
"X O \n",
"X O X \n",
"Episode 23, Total Reward: 1\n",
"Average Reward: 0.391304347826087\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
"O \n",
" \n",
"on move: O\n",
"X \n",
"O X \n",
" \n",
"on move: X\n",
"X \n",
"O X \n",
"O \n",
"on move: O\n",
"X \n",
"O X \n",
"O X \n",
"on move: X\n",
"X \n",
"O X \n",
"O X O \n",
"on move: O\n",
"X \n",
"O X X \n",
"O X O \n",
"on move: X\n",
"X O \n",
"O X X \n",
"O X O \n",
"on move: O\n",
"X O X \n",
"O X X \n",
"O X O \n",
"Episode 24, Total Reward: 0\n",
"Average Reward: 0.375\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" \n",
" X \n",
" X O \n",
"on move: X\n",
" \n",
"O X \n",
" X O \n",
"on move: O\n",
" \n",
"O X \n",
"X X O \n",
"on move: X\n",
" \n",
"O X O \n",
"X X O \n",
"on move: O\n",
" X \n",
"O X O \n",
"X X O \n",
"Episode 25, Total Reward: 1\n",
"Average Reward: 0.4\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
"O \n",
" \n",
"on move: O\n",
"X X \n",
"O \n",
" \n",
"on move: X\n",
"X X O \n",
"O \n",
" \n",
"on move: O\n",
"X X O \n",
"O X \n",
" \n",
"on move: X\n",
"X X O \n",
"O O X \n",
" \n",
"on move: O\n",
"X X O \n",
"O O X \n",
"X \n",
"on move: X\n",
"X X O \n",
"O O X \n",
"X O \n",
"on move: O\n",
"X X O \n",
"O O X \n",
"X O X \n",
"Episode 26, Total Reward: 0\n",
"Average Reward: 0.38461538461538464\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" O \n",
"X \n",
" \n",
"on move: O\n",
" O \n",
"X X \n",
" \n",
"on move: X\n",
" O \n",
"X X \n",
" O \n",
"on move: O\n",
" O \n",
"X X \n",
" O X \n",
"on move: X\n",
" O \n",
"X X \n",
"O O X \n",
"on move: O\n",
" O \n",
"X X X \n",
"O O X \n",
"Episode 27, Total Reward: 1\n",
"Average Reward: 0.4074074074074074\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
"O \n",
"X \n",
" \n",
"on move: O\n",
"O \n",
"X \n",
" X \n",
"on move: X\n",
"O O \n",
"X \n",
" X \n",
"on move: O\n",
"O O \n",
"X \n",
"X X \n",
"on move: X\n",
"O O O \n",
"X \n",
"X X \n",
"Episode 28, Total Reward: -1\n",
"Average Reward: 0.35714285714285715\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
" O \n",
"on move: O\n",
" \n",
"X X \n",
" O \n",
"on move: X\n",
" O \n",
"X X \n",
" O \n",
"on move: O\n",
" X O \n",
"X X \n",
" O \n",
"on move: X\n",
" X O \n",
"X X \n",
"O O \n",
"on move: O\n",
"X X O \n",
"X X \n",
"O O \n",
"on move: X\n",
"X X O \n",
"X X O \n",
"O O \n",
"on move: O\n",
"X X O \n",
"X X O \n",
"O O X \n",
"Episode 29, Total Reward: 1\n",
"Average Reward: 0.3793103448275862\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X O \n",
" \n",
"on move: O\n",
" \n",
"X O \n",
" X \n",
"on move: X\n",
" \n",
"X O \n",
" X O \n",
"on move: O\n",
" \n",
"X O \n",
"X X O \n",
"on move: X\n",
" \n",
"X O O \n",
"X X O \n",
"on move: O\n",
"X \n",
"X O O \n",
"X X O \n",
"Episode 30, Total Reward: 1\n",
"Average Reward: 0.4\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" O X \n",
" \n",
"on move: O\n",
" X \n",
" O X \n",
" \n",
"on move: X\n",
"O X \n",
" O X \n",
" \n",
"on move: O\n",
"O X \n",
" O X \n",
" X \n",
"on move: X\n",
"O X \n",
" O X \n",
"O X \n",
"on move: O\n",
"O X X \n",
" O X \n",
"O X \n",
"on move: X\n",
"O X X \n",
" O X \n",
"O X O \n",
"Episode 31, Total Reward: -1\n",
"Average Reward: 0.3548387096774194\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
"O \n",
" \n",
" X \n",
"on move: O\n",
"O \n",
" X \n",
" X \n",
"on move: X\n",
"O O \n",
" X \n",
" X \n",
"on move: O\n",
"O O \n",
" X \n",
"X X \n",
"on move: X\n",
"O O \n",
" X O \n",
"X X \n",
"on move: O\n",
"O O \n",
"X X O \n",
"X X \n",
"on move: X\n",
"O O O \n",
"X X O \n",
"X X \n",
"Episode 32, Total Reward: -1\n",
"Average Reward: 0.3125\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
" O \n",
"on move: O\n",
" X \n",
" \n",
" X O \n",
"on move: X\n",
"O X \n",
" \n",
" X O \n",
"on move: O\n",
"O X \n",
" X \n",
" X O \n",
"on move: X\n",
"O X \n",
"O X \n",
" X O \n",
"on move: O\n",
"O X \n",
"O X \n",
"X X O \n",
"on move: X\n",
"O X O \n",
"O X \n",
"X X O \n",
"on move: O\n",
"O X O \n",
"O X X \n",
"X X O \n",
"Episode 33, Total Reward: 1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
"O \n",
"X \n",
" \n",
"on move: O\n",
"O X \n",
"X \n",
" \n",
"on move: X\n",
"O X \n",
"X \n",
"O \n",
"on move: O\n",
"O X \n",
"X \n",
"O X \n",
"on move: X\n",
"O X O \n",
"X \n",
"O X \n",
"on move: O\n",
"O X O \n",
"X X \n",
"O X \n",
"on move: X\n",
"O X O \n",
"X X O \n",
"O X \n",
"on move: O\n",
"O X O \n",
"X X O \n",
"O X X \n",
"Episode 34, Total Reward: 1\n",
"Average Reward: 0.35294117647058826\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" O X \n",
" \n",
" \n",
"on move: O\n",
" O X \n",
" \n",
"X \n",
"on move: X\n",
"O O X \n",
" \n",
"X \n",
"on move: O\n",
"O O X \n",
" \n",
"X X \n",
"on move: X\n",
"O O X \n",
"O \n",
"X X \n",
"on move: O\n",
"O O X \n",
"O X \n",
"X X \n",
"Episode 35, Total Reward: 1\n",
"Average Reward: 0.37142857142857144\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" O \n",
"X \n",
"on move: O\n",
" X \n",
" O \n",
"X \n",
"on move: X\n",
" X \n",
" O \n",
"X O \n",
"on move: O\n",
" X X \n",
" O \n",
"X O \n",
"on move: X\n",
" X X \n",
" O O \n",
"X O \n",
"on move: O\n",
"X X X \n",
" O O \n",
"X O \n",
"Episode 36, Total Reward: 1\n",
"Average Reward: 0.3888888888888889\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
"O \n",
"X \n",
"on move: O\n",
" \n",
"O \n",
"X X \n",
"on move: X\n",
"O \n",
"O \n",
"X X \n",
"on move: O\n",
"O \n",
"O X \n",
"X X \n",
"on move: X\n",
"O O \n",
"O X \n",
"X X \n",
"on move: O\n",
"O O \n",
"O X \n",
"X X X \n",
"Episode 37, Total Reward: 1\n",
"Average Reward: 0.40540540540540543\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" O \n",
" X \n",
" \n",
"on move: O\n",
" O \n",
" X \n",
" X \n",
"on move: X\n",
" O \n",
"O X \n",
" X \n",
"on move: O\n",
"X O \n",
"O X \n",
" X \n",
"Episode 38, Total Reward: 1\n",
"Average Reward: 0.42105263157894735\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
"O \n",
"X \n",
"on move: O\n",
" X \n",
"O \n",
"X \n",
"on move: X\n",
" O X \n",
"O \n",
"X \n",
"on move: O\n",
" O X \n",
"O \n",
"X X \n",
"on move: X\n",
" O X \n",
"O \n",
"X O X \n",
"on move: O\n",
" O X \n",
"O X \n",
"X O X \n",
"Episode 39, Total Reward: 1\n",
"Average Reward: 0.4358974358974359\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
"O \n",
" X \n",
"on move: O\n",
" \n",
"O \n",
" X X \n",
"on move: X\n",
" \n",
"O O \n",
" X X \n",
"on move: O\n",
" \n",
"O O X \n",
" X X \n",
"on move: X\n",
"O \n",
"O O X \n",
" X X \n",
"on move: O\n",
"O X \n",
"O O X \n",
" X X \n",
"Episode 40, Total Reward: 1\n",
"Average Reward: 0.45\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
"O \n",
"on move: O\n",
" X \n",
"X \n",
"O \n",
"on move: X\n",
" X \n",
"X \n",
"O O \n",
"on move: O\n",
" X \n",
"X X \n",
"O O \n",
"on move: X\n",
" X \n",
"X X \n",
"O O O \n",
"Episode 41, Total Reward: -1\n",
"Average Reward: 0.4146341463414634\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" \n",
"X O \n",
"on move: O\n",
" \n",
"X \n",
"X O \n",
"on move: X\n",
" O \n",
"X \n",
"X O \n",
"on move: O\n",
" O \n",
"X \n",
"X X O \n",
"on move: X\n",
" O \n",
"X O \n",
"X X O \n",
"on move: O\n",
"X O \n",
"X O \n",
"X X O \n",
"Episode 42, Total Reward: 1\n",
"Average Reward: 0.42857142857142855\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X \n",
"X O \n",
" \n",
"on move: X\n",
" X \n",
"X O O \n",
" \n",
"on move: O\n",
" X X \n",
"X O O \n",
" \n",
"on move: X\n",
"O X X \n",
"X O O \n",
" \n",
"on move: O\n",
"O X X \n",
"X O O \n",
" X \n",
"on move: X\n",
"O X X \n",
"X O O \n",
" X O \n",
"Episode 43, Total Reward: -1\n",
"Average Reward: 0.3953488372093023\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
"O \n",
"on move: O\n",
" \n",
" X \n",
"O X \n",
"on move: X\n",
" O \n",
" X \n",
"O X \n",
"on move: O\n",
" O X \n",
" X \n",
"O X \n",
"on move: X\n",
" O X \n",
" X \n",
"O X O \n",
"on move: O\n",
" O X \n",
"X X \n",
"O X O \n",
"on move: X\n",
" O X \n",
"X X O \n",
"O X O \n",
"on move: O\n",
"X O X \n",
"X X O \n",
"O X O \n",
"Episode 44, Total Reward: 0\n",
"Average Reward: 0.38636363636363635\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X \n",
" O \n",
" X \n",
"on move: X\n",
" X \n",
"O O \n",
" X \n",
"on move: O\n",
" X \n",
"O O \n",
"X X \n",
"on move: X\n",
" X \n",
"O O O \n",
"X X \n",
"Episode 45, Total Reward: -1\n",
"Average Reward: 0.35555555555555557\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" O \n",
" \n",
" X X \n",
"on move: X\n",
"O O \n",
" \n",
" X X \n",
"on move: O\n",
"O O \n",
" X \n",
" X X \n",
"on move: X\n",
"O O \n",
" X \n",
"O X X \n",
"on move: O\n",
"O O \n",
"X X \n",
"O X X \n",
"on move: X\n",
"O O O \n",
"X X \n",
"O X X \n",
"Episode 46, Total Reward: -1\n",
"Average Reward: 0.32608695652173914\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
"O \n",
" \n",
"X \n",
"on move: O\n",
"O \n",
" X \n",
"X \n",
"on move: X\n",
"O O \n",
" X \n",
"X \n",
"on move: O\n",
"O O \n",
" X X \n",
"X \n",
"on move: X\n",
"O O \n",
"O X X \n",
"X \n",
"on move: O\n",
"O O X \n",
"O X X \n",
"X \n",
"Episode 47, Total Reward: 1\n",
"Average Reward: 0.3404255319148936\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
"O \n",
"on move: O\n",
" X X \n",
" \n",
"O \n",
"on move: X\n",
" X X \n",
" \n",
"O O \n",
"on move: O\n",
"X X X \n",
" \n",
"O O \n",
"Episode 48, Total Reward: 1\n",
"Average Reward: 0.3541666666666667\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" \n",
" X X \n",
" O \n",
"on move: X\n",
" O \n",
" X X \n",
" O \n",
"on move: O\n",
"X O \n",
" X X \n",
" O \n",
"on move: X\n",
"X O \n",
" X X \n",
" O O \n",
"on move: O\n",
"X O \n",
" X X \n",
"X O O \n",
"on move: X\n",
"X O \n",
"O X X \n",
"X O O \n",
"on move: O\n",
"X O X \n",
"O X X \n",
"X O O \n",
"Episode 49, Total Reward: 1\n",
"Average Reward: 0.3673469387755102\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
"O \n",
" \n",
" X \n",
"on move: O\n",
"O \n",
" \n",
" X X \n",
"on move: X\n",
"O \n",
" \n",
"O X X \n",
"on move: O\n",
"O X \n",
" \n",
"O X X \n",
"on move: X\n",
"O X \n",
"O \n",
"O X X \n",
"Episode 50, Total Reward: -1\n",
"Average Reward: 0.34\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X \n",
" X O \n",
" \n",
"on move: X\n",
" X \n",
"O X O \n",
" \n",
"on move: O\n",
" X \n",
"O X O \n",
"X \n",
"on move: X\n",
" X \n",
"O X O \n",
"X O \n",
"on move: O\n",
"X X \n",
"O X O \n",
"X O \n",
"on move: X\n",
"X X \n",
"O X O \n",
"X O O \n",
"on move: O\n",
"X X X \n",
"O X O \n",
"X O O \n",
"Episode 51, Total Reward: 1\n",
"Average Reward: 0.35294117647058826\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" O \n",
" X \n",
" X \n",
"on move: X\n",
" O O \n",
" X \n",
" X \n",
"on move: O\n",
" O O \n",
" X \n",
" X X \n",
"on move: X\n",
" O O \n",
"O X \n",
" X X \n",
"on move: O\n",
" O O \n",
"O X \n",
"X X X \n",
"Episode 52, Total Reward: 1\n",
"Average Reward: 0.36538461538461536\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" O \n",
"X \n",
" \n",
"on move: O\n",
"X O \n",
"X \n",
" \n",
"on move: X\n",
"X O \n",
"X O \n",
" \n",
"on move: O\n",
"X O \n",
"X O \n",
"X \n",
"Episode 53, Total Reward: 1\n",
"Average Reward: 0.37735849056603776\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
"O \n",
" \n",
" X \n",
"on move: O\n",
"O \n",
"X \n",
" X \n",
"on move: X\n",
"O \n",
"X O \n",
" X \n",
"on move: O\n",
"O \n",
"X O X \n",
" X \n",
"on move: X\n",
"O \n",
"X O X \n",
" O X \n",
"on move: O\n",
"O X \n",
"X O X \n",
" O X \n",
"on move: X\n",
"O X O \n",
"X O X \n",
" O X \n",
"on move: O\n",
"O X O \n",
"X O X \n",
"X O X \n",
"Episode 54, Total Reward: 0\n",
"Average Reward: 0.37037037037037035\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
"O X \n",
" \n",
"on move: O\n",
" X \n",
"O X \n",
" \n",
"on move: X\n",
" X \n",
"O X \n",
" O \n",
"on move: O\n",
"X X \n",
"O X \n",
" O \n",
"on move: X\n",
"X X \n",
"O O X \n",
" O \n",
"on move: O\n",
"X X \n",
"O O X \n",
" X O \n",
"on move: X\n",
"X X \n",
"O O X \n",
"O X O \n",
"on move: O\n",
"X X X \n",
"O O X \n",
"O X O \n",
"Episode 55, Total Reward: 1\n",
"Average Reward: 0.38181818181818183\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" \n",
" X O \n",
"on move: O\n",
" \n",
"X \n",
" X O \n",
"on move: X\n",
" \n",
"X O \n",
" X O \n",
"on move: O\n",
" X \n",
"X O \n",
" X O \n",
"on move: X\n",
" X \n",
"X O O \n",
" X O \n",
"on move: O\n",
" X \n",
"X O O \n",
"X X O \n",
"on move: X\n",
"O X \n",
"X O O \n",
"X X O \n",
"Episode 56, Total Reward: -1\n",
"Average Reward: 0.35714285714285715\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" O \n",
" X \n",
" \n",
"on move: O\n",
" O \n",
"X X \n",
" \n",
"on move: X\n",
" O \n",
"X X \n",
"O \n",
"on move: O\n",
" O \n",
"X X \n",
"O X \n",
"on move: X\n",
" O \n",
"X X \n",
"O O X \n",
"on move: O\n",
" O \n",
"X X X \n",
"O O X \n",
"Episode 57, Total Reward: 1\n",
"Average Reward: 0.3684210526315789\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" \n",
"X O \n",
"on move: O\n",
" X \n",
" \n",
"X O \n",
"on move: X\n",
" X \n",
" O \n",
"X O \n",
"on move: O\n",
" X \n",
" O \n",
"X O X \n",
"on move: X\n",
" O X \n",
" O \n",
"X O X \n",
"Episode 58, Total Reward: -1\n",
"Average Reward: 0.3448275862068966\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
"O \n",
"X \n",
" \n",
"on move: O\n",
"O \n",
"X \n",
"X \n",
"on move: X\n",
"O O \n",
"X \n",
"X \n",
"on move: O\n",
"O O \n",
"X X \n",
"X \n",
"on move: X\n",
"O O O \n",
"X X \n",
"X \n",
"Episode 59, Total Reward: -1\n",
"Average Reward: 0.3220338983050847\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" O \n",
" \n",
"X \n",
"on move: O\n",
"X O \n",
" \n",
"X \n",
"on move: X\n",
"X O O \n",
" \n",
"X \n",
"on move: O\n",
"X O O \n",
" X \n",
"X \n",
"on move: X\n",
"X O O \n",
" O X \n",
"X \n",
"on move: O\n",
"X O O \n",
"X O X \n",
"X \n",
"Episode 60, Total Reward: 1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
" X \n",
" X O \n",
" O \n",
"on move: O\n",
"X X \n",
" X O \n",
" O \n",
"on move: X\n",
"X X \n",
" X O \n",
" O O \n",
"on move: O\n",
"X X X \n",
" X O \n",
" O O \n",
"Episode 61, Total Reward: 1\n",
"Average Reward: 0.3442622950819672\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
"O \n",
" \n",
"on move: O\n",
" X \n",
"O X \n",
" \n",
"on move: X\n",
" X O \n",
"O X \n",
" \n",
"on move: O\n",
" X O \n",
"O X \n",
" X \n",
"Episode 62, Total Reward: 1\n",
"Average Reward: 0.3548387096774194\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
" O \n",
"on move: O\n",
" \n",
"X X \n",
" O \n",
"on move: X\n",
" \n",
"X X \n",
"O O \n",
"on move: O\n",
"X \n",
"X X \n",
"O O \n",
"on move: X\n",
"X O \n",
"X X \n",
"O O \n",
"on move: O\n",
"X O X \n",
"X X \n",
"O O \n",
"on move: X\n",
"X O X \n",
"X O X \n",
"O O \n",
"Episode 63, Total Reward: -1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X O \n",
" \n",
"on move: O\n",
" \n",
"X X O \n",
" \n",
"on move: X\n",
" \n",
"X X O \n",
"O \n",
"on move: O\n",
"X \n",
"X X O \n",
"O \n",
"on move: X\n",
"X O \n",
"X X O \n",
"O \n",
"on move: O\n",
"X O \n",
"X X O \n",
"O X \n",
"on move: X\n",
"X O \n",
"X X O \n",
"O X O \n",
"on move: O\n",
"X O X \n",
"X X O \n",
"O X O \n",
"Episode 64, Total Reward: 0\n",
"Average Reward: 0.328125\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
"O \n",
" \n",
"X \n",
"on move: O\n",
"O \n",
" X \n",
"X \n",
"on move: X\n",
"O O \n",
" X \n",
"X \n",
"on move: O\n",
"O O X \n",
" X \n",
"X \n",
"on move: X\n",
"O O X \n",
" X \n",
"X O \n",
"on move: O\n",
"O O X \n",
" X \n",
"X O X \n",
"Episode 65, Total Reward: 1\n",
"Average Reward: 0.3384615384615385\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
"O \n",
" \n",
" X \n",
"on move: O\n",
"O \n",
" X \n",
" X \n",
"on move: X\n",
"O O \n",
" X \n",
" X \n",
"on move: O\n",
"O O \n",
"X X \n",
" X \n",
"on move: X\n",
"O O \n",
"X X O \n",
" X \n",
"on move: O\n",
"O O \n",
"X X O \n",
"X X \n",
"on move: X\n",
"O O \n",
"X X O \n",
"X O X \n",
"on move: O\n",
"O O X \n",
"X X O \n",
"X O X \n",
"Episode 66, Total Reward: 1\n",
"Average Reward: 0.3484848484848485\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" O \n",
" \n",
"on move: O\n",
"X \n",
" O \n",
" X \n",
"on move: X\n",
"X O \n",
" O \n",
" X \n",
"on move: O\n",
"X O \n",
"X O \n",
" X \n",
"on move: X\n",
"X O \n",
"X O \n",
"O X \n",
"on move: O\n",
"X O \n",
"X O \n",
"O X X \n",
"on move: X\n",
"X O O \n",
"X O \n",
"O X X \n",
"on move: O\n",
"X O O \n",
"X X O \n",
"O X X \n",
"Episode 67, Total Reward: 1\n",
"Average Reward: 0.3582089552238806\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
"O X \n",
" \n",
"on move: O\n",
" X \n",
"O X \n",
" \n",
"on move: X\n",
" X O \n",
"O X \n",
" \n",
"on move: O\n",
" X O \n",
"O X X \n",
" \n",
"on move: X\n",
"O X O \n",
"O X X \n",
" \n",
"on move: O\n",
"O X O \n",
"O X X \n",
" X \n",
"on move: X\n",
"O X O \n",
"O X X \n",
" O X \n",
"on move: O\n",
"O X O \n",
"O X X \n",
"X O X \n",
"Episode 68, Total Reward: 0\n",
"Average Reward: 0.35294117647058826\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" O X \n",
" \n",
" X \n",
"on move: X\n",
" O X \n",
" \n",
"O X \n",
"on move: O\n",
"X O X \n",
" \n",
"O X \n",
"on move: X\n",
"X O X \n",
" O \n",
"O X \n",
"on move: O\n",
"X O X \n",
"X O \n",
"O X \n",
"on move: X\n",
"X O X \n",
"X O O \n",
"O X \n",
"on move: O\n",
"X O X \n",
"X O O \n",
"O X X \n",
"Episode 69, Total Reward: 0\n",
"Average Reward: 0.34782608695652173\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
"O X \n",
" X \n",
" O \n",
"on move: O\n",
"O X X \n",
" X \n",
" O \n",
"on move: X\n",
"O X X \n",
" X \n",
" O O \n",
"on move: O\n",
"O X X \n",
" X X \n",
" O O \n",
"on move: X\n",
"O X X \n",
" X X \n",
"O O O \n",
"Episode 70, Total Reward: -1\n",
"Average Reward: 0.32857142857142857\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" \n",
" O X \n",
"on move: O\n",
" \n",
" X \n",
" O X \n",
"on move: X\n",
" \n",
" X O \n",
" O X \n",
"on move: O\n",
" X \n",
" X O \n",
" O X \n",
"on move: X\n",
" X \n",
"O X O \n",
" O X \n",
"on move: O\n",
"X X \n",
"O X O \n",
" O X \n",
"Episode 71, Total Reward: 1\n",
"Average Reward: 0.3380281690140845\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" O \n",
"X \n",
" \n",
"on move: O\n",
" O \n",
"X X \n",
" \n",
"on move: X\n",
" O O \n",
"X X \n",
" \n",
"on move: O\n",
"X O O \n",
"X X \n",
" \n",
"on move: X\n",
"X O O \n",
"X X \n",
" O \n",
"on move: O\n",
"X O O \n",
"X X \n",
" X O \n",
"on move: X\n",
"X O O \n",
"X X \n",
"O X O \n",
"on move: O\n",
"X O O \n",
"X X X \n",
"O X O \n",
"Episode 72, Total Reward: 1\n",
"Average Reward: 0.3472222222222222\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" \n",
"O X \n",
"on move: O\n",
" \n",
" X \n",
"O X \n",
"on move: X\n",
"O \n",
" X \n",
"O X \n",
"on move: O\n",
"O X \n",
" X \n",
"O X \n",
"on move: X\n",
"O X \n",
"O X \n",
"O X \n",
"Episode 73, Total Reward: -1\n",
"Average Reward: 0.3287671232876712\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" O X \n",
" \n",
"on move: O\n",
" \n",
"X O X \n",
" \n",
"on move: X\n",
" \n",
"X O X \n",
"O \n",
"on move: O\n",
"X \n",
"X O X \n",
"O \n",
"on move: X\n",
"X O \n",
"X O X \n",
"O \n",
"Episode 74, Total Reward: -1\n",
"Average Reward: 0.3108108108108108\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" O \n",
" X \n",
"on move: O\n",
" \n",
"X O \n",
" X \n",
"on move: X\n",
" O \n",
"X O \n",
" X \n",
"on move: O\n",
" O \n",
"X X O \n",
" X \n",
"on move: X\n",
" O \n",
"X X O \n",
"O X \n",
"on move: O\n",
" O \n",
"X X O \n",
"O X X \n",
"on move: X\n",
"O O \n",
"X X O \n",
"O X X \n",
"on move: O\n",
"O X O \n",
"X X O \n",
"O X X \n",
"Episode 75, Total Reward: 1\n",
"Average Reward: 0.32\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X O \n",
" \n",
"on move: O\n",
" X \n",
"X O \n",
" \n",
"on move: X\n",
"O X \n",
"X O \n",
" \n",
"on move: O\n",
"O X \n",
"X O \n",
" X \n",
"on move: X\n",
"O X \n",
"X O O \n",
" X \n",
"on move: O\n",
"O X X \n",
"X O O \n",
" X \n",
"on move: X\n",
"O X X \n",
"X O O \n",
" O X \n",
"on move: O\n",
"O X X \n",
"X O O \n",
"X O X \n",
"Episode 76, Total Reward: 0\n",
"Average Reward: 0.3157894736842105\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" \n",
"X O \n",
"on move: O\n",
" \n",
"X \n",
"X O \n",
"on move: X\n",
" O \n",
"X \n",
"X O \n",
"on move: O\n",
"X O \n",
"X \n",
"X O \n",
"Episode 77, Total Reward: 1\n",
"Average Reward: 0.3246753246753247\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" O \n",
" X \n",
" \n",
"on move: O\n",
" O \n",
" X \n",
" X \n",
"on move: X\n",
" O \n",
" X \n",
" O X \n",
"on move: O\n",
" O X \n",
" X \n",
" O X \n",
"Episode 78, Total Reward: 1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" O \n",
" \n",
" X X \n",
"on move: X\n",
" O O \n",
" \n",
" X X \n",
"on move: O\n",
"X O O \n",
" \n",
" X X \n",
"on move: X\n",
"X O O \n",
" O \n",
" X X \n",
"on move: O\n",
"X O O \n",
" O X \n",
" X X \n",
"on move: X\n",
"X O O \n",
" O X \n",
"O X X \n",
"Episode 79, Total Reward: -1\n",
"Average Reward: 0.31645569620253167\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
" X \n",
"O X \n",
" O \n",
"on move: O\n",
" X \n",
"O X \n",
"X O \n",
"on move: X\n",
"O X \n",
"O X \n",
"X O \n",
"on move: O\n",
"O X \n",
"O X X \n",
"X O \n",
"on move: X\n",
"O X \n",
"O X X \n",
"X O O \n",
"on move: O\n",
"O X X \n",
"O X X \n",
"X O O \n",
"Episode 80, Total Reward: 1\n",
"Average Reward: 0.325\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
"O \n",
"on move: O\n",
" X \n",
" X \n",
"O \n",
"on move: X\n",
" X \n",
"O X \n",
"O \n",
"on move: O\n",
"X X \n",
"O X \n",
"O \n",
"on move: X\n",
"X X \n",
"O X O \n",
"O \n",
"on move: O\n",
"X X \n",
"O X O \n",
"O X \n",
"Episode 81, Total Reward: 1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
"O \n",
" X \n",
" \n",
"on move: O\n",
"O \n",
" X X \n",
" \n",
"on move: X\n",
"O \n",
"O X X \n",
" \n",
"on move: O\n",
"O \n",
"O X X \n",
" X \n",
"on move: X\n",
"O O \n",
"O X X \n",
" X \n",
"on move: O\n",
"O O \n",
"O X X \n",
"X X \n",
"on move: X\n",
"O O \n",
"O X X \n",
"X O X \n",
"on move: O\n",
"O X O \n",
"O X X \n",
"X O X \n",
"Episode 82, Total Reward: 0\n",
"Average Reward: 0.32926829268292684\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
"O X \n",
" \n",
"on move: O\n",
" \n",
"O X \n",
" X \n",
"on move: X\n",
" O \n",
"O X \n",
" X \n",
"on move: O\n",
" X O \n",
"O X \n",
" X \n",
"on move: X\n",
"O X O \n",
"O X \n",
" X \n",
"on move: O\n",
"O X O \n",
"O X \n",
" X X \n",
"on move: X\n",
"O X O \n",
"O O X \n",
" X X \n",
"on move: O\n",
"O X O \n",
"O O X \n",
"X X X \n",
"Episode 83, Total Reward: 1\n",
"Average Reward: 0.3373493975903614\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
"O X \n",
" \n",
"on move: O\n",
" \n",
"O X \n",
" X \n",
"on move: X\n",
"O \n",
"O X \n",
" X \n",
"on move: O\n",
"O X \n",
"O X \n",
" X \n",
"on move: X\n",
"O X \n",
"O X \n",
"O X \n",
"Episode 84, Total Reward: -1\n",
"Average Reward: 0.32142857142857145\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
"O X \n",
" \n",
"on move: O\n",
" \n",
"O X \n",
" X \n",
"on move: X\n",
" \n",
"O X \n",
" X O \n",
"on move: O\n",
" X \n",
"O X \n",
" X O \n",
"on move: X\n",
" O X \n",
"O X \n",
" X O \n",
"on move: O\n",
" O X \n",
"O X X \n",
" X O \n",
"on move: X\n",
" O X \n",
"O X X \n",
"O X O \n",
"on move: O\n",
"X O X \n",
"O X X \n",
"O X O \n",
"Episode 85, Total Reward: 0\n",
"Average Reward: 0.3176470588235294\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" O \n",
" \n",
" X X \n",
"on move: X\n",
"O O \n",
" \n",
" X X \n",
"on move: O\n",
"O O \n",
" X \n",
" X X \n",
"on move: X\n",
"O O \n",
"O X \n",
" X X \n",
"on move: O\n",
"O X O \n",
"O X \n",
" X X \n",
"Episode 86, Total Reward: 1\n",
"Average Reward: 0.32558139534883723\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
" O \n",
"on move: O\n",
"X X \n",
" \n",
" O \n",
"on move: X\n",
"X X \n",
" O \n",
" O \n",
"on move: O\n",
"X X \n",
"X O \n",
" O \n",
"on move: X\n",
"X X O \n",
"X O \n",
" O \n",
"on move: O\n",
"X X O \n",
"X O \n",
" O X \n",
"on move: X\n",
"X X O \n",
"X O O \n",
" O X \n",
"on move: O\n",
"X X O \n",
"X O O \n",
"X O X \n",
"Episode 87, Total Reward: 1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" O \n",
" X \n",
"on move: O\n",
" \n",
" O \n",
" X X \n",
"on move: X\n",
" \n",
"O O \n",
" X X \n",
"on move: O\n",
"X \n",
"O O \n",
" X X \n",
"on move: X\n",
"X \n",
"O O \n",
"O X X \n",
"on move: O\n",
"X X \n",
"O O \n",
"O X X \n",
"on move: X\n",
"X O X \n",
"O O \n",
"O X X \n",
"on move: O\n",
"X O X \n",
"O O X \n",
"O X X \n",
"Episode 88, Total Reward: 1\n",
"Average Reward: 0.3409090909090909\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" \n",
" X \n",
" X O \n",
"on move: X\n",
" \n",
" X \n",
"O X O \n",
"on move: O\n",
"X \n",
" X \n",
"O X O \n",
"on move: X\n",
"X \n",
" O X \n",
"O X O \n",
"on move: O\n",
"X X \n",
" O X \n",
"O X O \n",
"on move: X\n",
"X O X \n",
" O X \n",
"O X O \n",
"on move: O\n",
"X O X \n",
"X O X \n",
"O X O \n",
"Episode 89, Total Reward: 0\n",
"Average Reward: 0.33707865168539325\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" O \n",
" X \n",
"on move: O\n",
"X \n",
" O \n",
" X \n",
"on move: X\n",
"X \n",
"O O \n",
" X \n",
"on move: O\n",
"X \n",
"O O X \n",
" X \n",
"on move: X\n",
"X O \n",
"O O X \n",
" X \n",
"on move: O\n",
"X O \n",
"O O X \n",
" X X \n",
"on move: X\n",
"X O \n",
"O O X \n",
"O X X \n",
"on move: O\n",
"X O X \n",
"O O X \n",
"O X X \n",
"Episode 90, Total Reward: 1\n",
"Average Reward: 0.34444444444444444\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" O \n",
"X \n",
"on move: O\n",
" \n",
" O \n",
"X X \n",
"on move: X\n",
" O \n",
" O \n",
"X X \n",
"on move: O\n",
" X O \n",
" O \n",
"X X \n",
"on move: X\n",
"O X O \n",
" O \n",
"X X \n",
"on move: O\n",
"O X O \n",
" X O \n",
"X X \n",
"on move: X\n",
"O X O \n",
" X O \n",
"X O X \n",
"on move: O\n",
"O X O \n",
"X X O \n",
"X O X \n",
"Episode 91, Total Reward: 0\n",
"Average Reward: 0.34065934065934067\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X \n",
" O \n",
" X \n",
"on move: X\n",
" X \n",
" O O \n",
" X \n",
"on move: O\n",
"X X \n",
" O O \n",
" X \n",
"on move: X\n",
"X X \n",
" O O \n",
"O X \n",
"on move: O\n",
"X X \n",
" O O \n",
"O X X \n",
"on move: X\n",
"X X \n",
"O O O \n",
"O X X \n",
"Episode 92, Total Reward: -1\n",
"Average Reward: 0.32608695652173914\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
"O X \n",
" \n",
" \n",
"on move: O\n",
"O X \n",
" \n",
" X \n",
"on move: X\n",
"O X \n",
"O \n",
" X \n",
"on move: O\n",
"O X \n",
"O X \n",
" X \n",
"Episode 93, Total Reward: 1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" \n",
" O \n",
"on move: O\n",
"X X \n",
" \n",
" O \n",
"on move: X\n",
"X X \n",
" \n",
" O O \n",
"on move: O\n",
"X X X \n",
" \n",
" O O \n",
"Episode 94, Total Reward: 1\n",
"Average Reward: 0.3404255319148936\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" \n",
" O \n",
"on move: O\n",
"X \n",
"X \n",
" O \n",
"on move: X\n",
"X \n",
"X \n",
"O O \n",
"on move: O\n",
"X X \n",
"X \n",
"O O \n",
"on move: X\n",
"X X \n",
"X O \n",
"O O \n",
"on move: O\n",
"X X \n",
"X O \n",
"O O X \n",
"on move: X\n",
"X X O \n",
"X O \n",
"O O X \n",
"Episode 95, Total Reward: -1\n",
"Average Reward: 0.3263157894736842\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" O \n",
"X \n",
"on move: O\n",
" \n",
" O \n",
"X X \n",
"on move: X\n",
" \n",
" O \n",
"X X O \n",
"on move: O\n",
" \n",
"X O \n",
"X X O \n",
"on move: X\n",
" O \n",
"X O \n",
"X X O \n",
"Episode 96, Total Reward: -1\n",
"Average Reward: 0.3125\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
" O \n",
"on move: O\n",
" X \n",
"X \n",
" O \n",
"on move: X\n",
" O X \n",
"X \n",
" O \n",
"on move: O\n",
" O X \n",
"X \n",
" O X \n",
"on move: X\n",
" O X \n",
"X \n",
"O O X \n",
"on move: O\n",
"X O X \n",
"X \n",
"O O X \n",
"on move: X\n",
"X O X \n",
"X O \n",
"O O X \n",
"on move: O\n",
"X O X \n",
"X X O \n",
"O O X \n",
"Episode 97, Total Reward: 1\n",
"Average Reward: 0.31958762886597936\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" O \n",
"X \n",
" \n",
"on move: O\n",
" O \n",
"X \n",
" X \n",
"on move: X\n",
" O \n",
"X O \n",
" X \n",
"on move: O\n",
"X O \n",
"X O \n",
" X \n",
"on move: X\n",
"X O \n",
"X O \n",
" O X \n",
"Episode 98, Total Reward: -1\n",
"Average Reward: 0.30612244897959184\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
"O \n",
"on move: O\n",
" \n",
"X \n",
"O X \n",
"on move: X\n",
"O \n",
"X \n",
"O X \n",
"on move: O\n",
"O \n",
"X X \n",
"O X \n",
"on move: X\n",
"O O \n",
"X X \n",
"O X \n",
"on move: O\n",
"O O \n",
"X X \n",
"O X X \n",
"on move: X\n",
"O O O \n",
"X X \n",
"O X X \n",
"Episode 99, Total Reward: -1\n",
"Average Reward: 0.29292929292929293\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" O \n",
" X \n",
" \n",
"on move: O\n",
" X O \n",
" X \n",
" \n",
"on move: X\n",
" X O \n",
" X \n",
" O \n",
"on move: O\n",
" X O \n",
" X \n",
" X O \n",
"Episode 100, Total Reward: 1\n",
"Average Reward: 0.3\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
" X \n",
" X \n",
" O O \n",
"on move: O\n",
" X X \n",
" X \n",
" O O \n",
"on move: X\n",
" X X \n",
" X O \n",
" O O \n",
"on move: O\n",
"X X X \n",
" X O \n",
" O O \n",
"Episode 101, Total Reward: 1\n",
"Average Reward: 0.3069306930693069\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
"X X \n",
" O \n",
" \n",
"on move: X\n",
"X X \n",
" O O \n",
" \n",
"on move: O\n",
"X X \n",
" O O \n",
" X \n",
"on move: X\n",
"X X O \n",
" O O \n",
" X \n",
"on move: O\n",
"X X O \n",
" O O \n",
"X X \n",
"on move: X\n",
"X X O \n",
"O O O \n",
"X X \n",
"Episode 102, Total Reward: -1\n",
"Average Reward: 0.29411764705882354\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" O X \n",
" \n",
"on move: O\n",
" \n",
" O X \n",
" X \n",
"on move: X\n",
"O \n",
" O X \n",
" X \n",
"on move: O\n",
"O X \n",
" O X \n",
" X \n",
"on move: X\n",
"O X \n",
" O X \n",
" O X \n",
"on move: O\n",
"O X \n",
"X O X \n",
" O X \n",
"on move: X\n",
"O X \n",
"X O X \n",
"O O X \n",
"on move: O\n",
"O X X \n",
"X O X \n",
"O O X \n",
"Episode 103, Total Reward: 1\n",
"Average Reward: 0.30097087378640774\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" \n",
" X X \n",
" O \n",
"on move: X\n",
" \n",
" X X \n",
" O O \n",
"on move: O\n",
"X \n",
" X X \n",
" O O \n",
"on move: X\n",
"X O \n",
" X X \n",
" O O \n",
"on move: O\n",
"X O \n",
"X X X \n",
" O O \n",
"Episode 104, Total Reward: 1\n",
"Average Reward: 0.3076923076923077\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X X \n",
" O \n",
" \n",
"on move: X\n",
" X X \n",
" O \n",
" O \n",
"on move: O\n",
"X X X \n",
" O \n",
" O \n",
"Episode 105, Total Reward: 1\n",
"Average Reward: 0.3142857142857143\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" O \n",
"X \n",
" \n",
"on move: O\n",
" O X \n",
"X \n",
" \n",
"on move: X\n",
" O X \n",
"X \n",
" O \n",
"on move: O\n",
" O X \n",
"X X \n",
" O \n",
"on move: X\n",
" O X \n",
"X X O \n",
" O \n",
"on move: O\n",
" O X \n",
"X X O \n",
" O X \n",
"on move: X\n",
" O X \n",
"X X O \n",
"O O X \n",
"on move: O\n",
"X O X \n",
"X X O \n",
"O O X \n",
"Episode 106, Total Reward: 1\n",
"Average Reward: 0.32075471698113206\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
"O \n",
" \n",
" X \n",
"on move: O\n",
"O \n",
" X \n",
" X \n",
"on move: X\n",
"O O \n",
" X \n",
" X \n",
"on move: O\n",
"O O \n",
" X \n",
" X X \n",
"on move: X\n",
"O O \n",
" O X \n",
" X X \n",
"on move: O\n",
"O X O \n",
" O X \n",
" X X \n",
"on move: X\n",
"O X O \n",
" O X \n",
"O X X \n",
"Episode 107, Total Reward: -1\n",
"Average Reward: 0.308411214953271\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" O \n",
" \n",
"X \n",
"on move: O\n",
" O \n",
"X \n",
"X \n",
"on move: X\n",
" O \n",
"X O \n",
"X \n",
"on move: O\n",
"X O \n",
"X O \n",
"X \n",
"Episode 108, Total Reward: 1\n",
"Average Reward: 0.3148148148148148\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
" X O \n",
" X \n",
" O \n",
"on move: O\n",
" X O \n",
" X \n",
" X O \n",
"on move: X\n",
" X O \n",
"O X \n",
" X O \n",
"on move: O\n",
" X O \n",
"O X X \n",
" X O \n",
"Episode 109, Total Reward: 1\n",
"Average Reward: 0.3211009174311927\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" \n",
" O \n",
"on move: O\n",
"X \n",
" \n",
"X O \n",
"on move: X\n",
"X \n",
" \n",
"X O O \n",
"on move: O\n",
"X \n",
" X \n",
"X O O \n",
"on move: X\n",
"X O \n",
" X \n",
"X O O \n",
"on move: O\n",
"X O \n",
"X X \n",
"X O O \n",
"Episode 110, Total Reward: 1\n",
"Average Reward: 0.32727272727272727\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" \n",
" X O \n",
"on move: O\n",
"X \n",
" \n",
" X O \n",
"on move: X\n",
"X O \n",
" \n",
" X O \n",
"on move: O\n",
"X X O \n",
" \n",
" X O \n",
"on move: X\n",
"X X O \n",
"O \n",
" X O \n",
"on move: O\n",
"X X O \n",
"O X \n",
" X O \n",
"Episode 111, Total Reward: 1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" \n",
" X \n",
" O X \n",
"on move: X\n",
" \n",
" X O \n",
" O X \n",
"on move: O\n",
"X \n",
" X O \n",
" O X \n",
"Episode 112, Total Reward: 1\n",
"Average Reward: 0.3392857142857143\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" \n",
" O X \n",
"on move: O\n",
" X \n",
" \n",
" O X \n",
"on move: X\n",
" X \n",
" \n",
"O O X \n",
"on move: O\n",
" X \n",
"X \n",
"O O X \n",
"on move: X\n",
" X \n",
"X O \n",
"O O X \n",
"on move: O\n",
" X \n",
"X X O \n",
"O O X \n",
"on move: X\n",
"O X \n",
"X X O \n",
"O O X \n",
"on move: O\n",
"O X X \n",
"X X O \n",
"O O X \n",
"Episode 113, Total Reward: 0\n",
"Average Reward: 0.336283185840708\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
"O \n",
" X \n",
" \n",
"on move: O\n",
"O X \n",
" X \n",
" \n",
"on move: X\n",
"O X \n",
" X \n",
" O \n",
"on move: O\n",
"O X \n",
" X \n",
" X O \n",
"on move: X\n",
"O O X \n",
" X \n",
" X O \n",
"on move: O\n",
"O O X \n",
" X X \n",
" X O \n",
"on move: X\n",
"O O X \n",
" X X \n",
"O X O \n",
"on move: O\n",
"O O X \n",
"X X X \n",
"O X O \n",
"Episode 114, Total Reward: 1\n",
"Average Reward: 0.34210526315789475\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
"O \n",
" X \n",
"on move: O\n",
"X \n",
"O \n",
" X \n",
"on move: X\n",
"X \n",
"O O \n",
" X \n",
"on move: O\n",
"X X \n",
"O O \n",
" X \n",
"on move: X\n",
"X X O \n",
"O O \n",
" X \n",
"on move: O\n",
"X X O \n",
"O O \n",
"X X \n",
"on move: X\n",
"X X O \n",
"O O \n",
"X O X \n",
"on move: O\n",
"X X O \n",
"O O X \n",
"X O X \n",
"Episode 115, Total Reward: 0\n",
"Average Reward: 0.3391304347826087\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" O \n",
" \n",
" X X \n",
"on move: X\n",
" O \n",
"O \n",
" X X \n",
"on move: O\n",
"X O \n",
"O \n",
" X X \n",
"on move: X\n",
"X O \n",
"O O \n",
" X X \n",
"on move: O\n",
"X O \n",
"O O \n",
"X X X \n",
"Episode 116, Total Reward: 1\n",
"Average Reward: 0.3448275862068966\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
" O \n",
"on move: O\n",
" X \n",
"X \n",
" O \n",
"on move: X\n",
" X \n",
"X O \n",
" O \n",
"on move: O\n",
" X \n",
"X O \n",
"X O \n",
"on move: X\n",
" X O \n",
"X O \n",
"X O \n",
"Episode 117, Total Reward: -1\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
"O \n",
" X \n",
"on move: O\n",
" X \n",
"O \n",
" X \n",
"on move: X\n",
" X \n",
"O O \n",
" X \n",
"on move: O\n",
" X X \n",
"O O \n",
" X \n",
"on move: X\n",
" X X \n",
"O O \n",
" O X \n",
"on move: O\n",
" X X \n",
"O O \n",
"X O X \n",
"on move: X\n",
"O X X \n",
"O O \n",
"X O X \n",
"on move: O\n",
"O X X \n",
"O X O \n",
"X O X \n",
"Episode 118, Total Reward: 1\n",
"Average Reward: 0.3389830508474576\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" O \n",
"X \n",
"on move: O\n",
" \n",
" O \n",
"X X \n",
"on move: X\n",
" \n",
" O \n",
"X O X \n",
"on move: O\n",
" X \n",
" O \n",
"X O X \n",
"on move: X\n",
"O X \n",
" O \n",
"X O X \n",
"on move: O\n",
"O X \n",
"X O \n",
"X O X \n",
"on move: X\n",
"O X \n",
"X O O \n",
"X O X \n",
"on move: O\n",
"O X X \n",
"X O O \n",
"X O X \n",
"Episode 119, Total Reward: 0\n",
"Average Reward: 0.33613445378151263\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
"O \n",
"X \n",
" \n",
"on move: O\n",
"O \n",
"X \n",
" X \n",
"on move: X\n",
"O \n",
"X O \n",
" X \n",
"on move: O\n",
"O X \n",
"X O \n",
" X \n",
"on move: X\n",
"O X \n",
"X O \n",
" O X \n",
"on move: O\n",
"O X \n",
"X O X \n",
" O X \n",
"on move: X\n",
"O X O \n",
"X O X \n",
" O X \n",
"on move: O\n",
"O X O \n",
"X O X \n",
"X O X \n",
"Episode 120, Total Reward: 0\n",
"Average Reward: 0.3333333333333333\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
"O \n",
" X \n",
" \n",
"on move: O\n",
"O \n",
" X \n",
" X \n",
"on move: X\n",
"O \n",
"O X \n",
" X \n",
"on move: O\n",
"O \n",
"O X \n",
"X X \n",
"on move: X\n",
"O \n",
"O X \n",
"X X O \n",
"on move: O\n",
"O X \n",
"O X \n",
"X X O \n",
"Episode 121, Total Reward: 1\n",
"Average Reward: 0.33884297520661155\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
"O \n",
"on move: O\n",
" X \n",
" X \n",
"O \n",
"on move: X\n",
" X \n",
"O X \n",
"O \n",
"on move: O\n",
"X X \n",
"O X \n",
"O \n",
"on move: X\n",
"X X \n",
"O O X \n",
"O \n",
"on move: O\n",
"X X \n",
"O O X \n",
"O X \n",
"on move: X\n",
"X X \n",
"O O X \n",
"O X O \n",
"on move: O\n",
"X X X \n",
"O O X \n",
"O X O \n",
"Episode 122, Total Reward: 1\n",
"Average Reward: 0.3442622950819672\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" \n",
" X \n",
" O X \n",
"on move: X\n",
" \n",
" X \n",
"O O X \n",
"on move: O\n",
"X \n",
" X \n",
"O O X \n",
"Episode 123, Total Reward: 1\n",
"Average Reward: 0.34959349593495936\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
"O \n",
" \n",
"on move: O\n",
"X \n",
"O X \n",
" \n",
"on move: X\n",
"X \n",
"O X O \n",
" \n",
"on move: O\n",
"X \n",
"O X O \n",
" X \n",
"on move: X\n",
"X \n",
"O X O \n",
"O X \n",
"on move: O\n",
"X \n",
"O X O \n",
"O X X \n",
"Episode 124, Total Reward: 1\n",
"Average Reward: 0.3548387096774194\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X \n",
" O \n",
" X \n",
"on move: X\n",
" X \n",
"O O \n",
" X \n",
"on move: O\n",
" X \n",
"O O \n",
"X X \n",
"on move: X\n",
" X \n",
"O O \n",
"X O X \n",
"on move: O\n",
" X \n",
"O X O \n",
"X O X \n",
"on move: X\n",
"O X \n",
"O X O \n",
"X O X \n",
"on move: O\n",
"O X X \n",
"O X O \n",
"X O X \n",
"Episode 125, Total Reward: 1\n",
"Average Reward: 0.36\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" \n",
"O \n",
"on move: O\n",
"X \n",
" \n",
"O X \n",
"on move: X\n",
"X \n",
" \n",
"O O X \n",
"on move: O\n",
"X \n",
" X \n",
"O O X \n",
"Episode 126, Total Reward: 1\n",
"Average Reward: 0.36507936507936506\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" \n",
"X O \n",
"on move: O\n",
" \n",
" X \n",
"X O \n",
"on move: X\n",
"O \n",
" X \n",
"X O \n",
"on move: O\n",
"O \n",
"X X \n",
"X O \n",
"on move: X\n",
"O O \n",
"X X \n",
"X O \n",
"on move: O\n",
"O O \n",
"X X X \n",
"X O \n",
"Episode 127, Total Reward: 1\n",
"Average Reward: 0.3700787401574803\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
" O \n",
"on move: O\n",
" \n",
"X \n",
"X O \n",
"on move: X\n",
"O \n",
"X \n",
"X O \n",
"on move: O\n",
"O \n",
"X X \n",
"X O \n",
"on move: X\n",
"O O \n",
"X X \n",
"X O \n",
"on move: O\n",
"O O \n",
"X X \n",
"X O X \n",
"on move: X\n",
"O O O \n",
"X X \n",
"X O X \n",
"Episode 128, Total Reward: -1\n",
"Average Reward: 0.359375\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
"X X \n",
" O \n",
" \n",
"on move: X\n",
"X X \n",
" O \n",
" O \n",
"on move: O\n",
"X X \n",
"X O \n",
" O \n",
"on move: X\n",
"X X \n",
"X O \n",
"O O \n",
"on move: O\n",
"X X \n",
"X O \n",
"O X O \n",
"on move: X\n",
"X X \n",
"X O O \n",
"O X O \n",
"on move: O\n",
"X X X \n",
"X O O \n",
"O X O \n",
"Episode 129, Total Reward: 1\n",
"Average Reward: 0.3643410852713178\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
" O \n",
"on move: O\n",
" \n",
"X \n",
"X O \n",
"on move: X\n",
" O \n",
"X \n",
"X O \n",
"on move: O\n",
" X O \n",
"X \n",
"X O \n",
"on move: X\n",
" X O \n",
"X \n",
"X O O \n",
"on move: O\n",
" X O \n",
"X X \n",
"X O O \n",
"on move: X\n",
" X O \n",
"X X O \n",
"X O O \n",
"Episode 130, Total Reward: -1\n",
"Average Reward: 0.35384615384615387\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
"O \n",
" \n",
" X \n",
"on move: O\n",
"O \n",
" X \n",
" X \n",
"on move: X\n",
"O \n",
"O X \n",
" X \n",
"on move: O\n",
"O X \n",
"O X \n",
" X \n",
"Episode 131, Total Reward: 1\n",
"Average Reward: 0.35877862595419846\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" \n",
" X \n",
"X O \n",
"on move: X\n",
" O \n",
" X \n",
"X O \n",
"on move: O\n",
" O \n",
"X X \n",
"X O \n",
"on move: X\n",
" O \n",
"X X O \n",
"X O \n",
"on move: O\n",
"X O \n",
"X X O \n",
"X O \n",
"Episode 132, Total Reward: 1\n",
"Average Reward: 0.36363636363636365\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X O \n",
" \n",
" \n",
"on move: O\n",
" X O \n",
" \n",
"X \n",
"on move: X\n",
" X O \n",
" O \n",
"X \n",
"on move: O\n",
"X X O \n",
" O \n",
"X \n",
"on move: X\n",
"X X O \n",
" O \n",
"X O \n",
"on move: O\n",
"X X O \n",
"X O \n",
"X O \n",
"Episode 133, Total Reward: 1\n",
"Average Reward: 0.3684210526315789\n",
"on move: O\n",
" \n",
"X \n",
" \n",
"on move: X\n",
" \n",
"X \n",
"O \n",
"on move: O\n",
" X \n",
"X \n",
"O \n",
"on move: X\n",
" X \n",
"X \n",
"O O \n",
"on move: O\n",
" X \n",
"X \n",
"O O X \n",
"on move: X\n",
"O X \n",
"X \n",
"O O X \n",
"on move: O\n",
"O X \n",
"X X \n",
"O O X \n",
"on move: X\n",
"O X O \n",
"X X \n",
"O O X \n",
"on move: O\n",
"O X O \n",
"X X X \n",
"O O X \n",
"Episode 134, Total Reward: 1\n",
"Average Reward: 0.373134328358209\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
"O X \n",
" \n",
" \n",
"on move: O\n",
"O X \n",
"X \n",
" \n",
"on move: X\n",
"O X \n",
"X \n",
" O \n",
"on move: O\n",
"O X \n",
"X X \n",
" O \n",
"on move: X\n",
"O X \n",
"X X O \n",
" O \n",
"on move: O\n",
"O X \n",
"X X O \n",
"X O \n",
"on move: X\n",
"O X O \n",
"X X O \n",
"X O \n",
"on move: O\n",
"O X O \n",
"X X O \n",
"X O X \n",
"Episode 135, Total Reward: 0\n",
"Average Reward: 0.37037037037037035\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" \n",
" O \n",
"on move: O\n",
"X X \n",
" \n",
" O \n",
"on move: X\n",
"X X \n",
" \n",
" O O \n",
"on move: O\n",
"X X X \n",
" \n",
" O O \n",
"Episode 136, Total Reward: 1\n",
"Average Reward: 0.375\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
" \n",
" \n",
"X O \n",
"on move: O\n",
"X \n",
" \n",
"X O \n",
"on move: X\n",
"X \n",
"O \n",
"X O \n",
"on move: O\n",
"X \n",
"O X \n",
"X O \n",
"on move: X\n",
"X O \n",
"O X \n",
"X O \n",
"on move: O\n",
"X X O \n",
"O X \n",
"X O \n",
"on move: X\n",
"X X O \n",
"O X O \n",
"X O \n",
"on move: O\n",
"X X O \n",
"O X O \n",
"X O X \n",
"Episode 137, Total Reward: 1\n",
"Average Reward: 0.3795620437956204\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X O \n",
" \n",
" \n",
"on move: O\n",
"X O \n",
" \n",
" X \n",
"on move: X\n",
"X O O \n",
" \n",
" X \n",
"on move: O\n",
"X O O \n",
" X \n",
" X \n",
"on move: X\n",
"X O O \n",
" X \n",
"O X \n",
"on move: O\n",
"X O O \n",
"X X \n",
"O X \n",
"on move: X\n",
"X O O \n",
"X X \n",
"O X O \n",
"on move: O\n",
"X O O \n",
"X X X \n",
"O X O \n",
"Episode 138, Total Reward: 1\n",
"Average Reward: 0.38405797101449274\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
"O X \n",
" X \n",
" O \n",
"on move: O\n",
"O X \n",
" X X \n",
" O \n",
"on move: X\n",
"O X \n",
" X X \n",
"O O \n",
"on move: O\n",
"O X X \n",
" X X \n",
"O O \n",
"on move: X\n",
"O X X \n",
"O X X \n",
"O O \n",
"Episode 139, Total Reward: -1\n",
"Average Reward: 0.37410071942446044\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" \n",
" \n",
" X O \n",
"on move: O\n",
" X \n",
" \n",
" X O \n",
"on move: X\n",
" X O \n",
" \n",
" X O \n",
"on move: O\n",
"X X O \n",
" \n",
" X O \n",
"on move: X\n",
"X X O \n",
"O \n",
" X O \n",
"on move: O\n",
"X X O \n",
"O \n",
"X X O \n",
"on move: X\n",
"X X O \n",
"O O \n",
"X X O \n",
"on move: O\n",
"X X O \n",
"O O X \n",
"X X O \n",
"Episode 140, Total Reward: 0\n",
"Average Reward: 0.37142857142857144\n",
"on move: O\n",
"X \n",
" \n",
" \n",
"on move: X\n",
"X \n",
" O \n",
" \n",
"on move: O\n",
"X X \n",
" O \n",
" \n",
"on move: X\n",
"X X \n",
" O \n",
"O \n",
"on move: O\n",
"X X \n",
" O \n",
"O X \n",
"on move: X\n",
"X X \n",
" O O \n",
"O X \n",
"on move: O\n",
"X X X \n",
" O O \n",
"O X \n",
"Episode 141, Total Reward: 1\n",
"Average Reward: 0.375886524822695\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" X \n",
" X \n",
" O \n",
"on move: X\n",
" X \n",
"O X \n",
" O \n",
"on move: O\n",
" X X \n",
"O X \n",
" O \n",
"on move: X\n",
"O X X \n",
"O X \n",
" O \n",
"on move: O\n",
"O X X \n",
"O X X \n",
" O \n",
"on move: X\n",
"O X X \n",
"O X X \n",
"O O \n",
"Episode 142, Total Reward: -1\n",
"Average Reward: 0.36619718309859156\n",
"on move: O\n",
" \n",
" \n",
" X \n",
"on move: X\n",
" O \n",
" \n",
" X \n",
"on move: O\n",
" O \n",
" \n",
" X X \n",
"on move: X\n",
" O \n",
" \n",
"O X X \n",
"on move: O\n",
" O \n",
" X \n",
"O X X \n",
"on move: X\n",
" O O \n",
" X \n",
"O X X \n",
"on move: O\n",
"X O O \n",
" X \n",
"O X X \n",
"on move: X\n",
"X O O \n",
" O X \n",
"O X X \n",
"Episode 143, Total Reward: -1\n",
"Average Reward: 0.35664335664335667\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
"O \n",
" \n",
"on move: O\n",
" X \n",
"O \n",
"X \n",
"on move: X\n",
" X \n",
"O O \n",
"X \n",
"on move: O\n",
" X \n",
"O O \n",
"X X \n",
"on move: X\n",
" X O \n",
"O O \n",
"X X \n",
"on move: O\n",
"X X O \n",
"O O \n",
"X X \n",
"on move: X\n",
"X X O \n",
"O O \n",
"X X O \n",
"on move: O\n",
"X X O \n",
"O O X \n",
"X X O \n",
"Episode 144, Total Reward: 0\n",
"Average Reward: 0.3541666666666667\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
"X X \n",
" O \n",
" \n",
"on move: X\n",
"X X \n",
" O \n",
"O \n",
"on move: O\n",
"X X \n",
"X O \n",
"O \n",
"on move: X\n",
"X X \n",
"X O O \n",
"O \n",
"on move: O\n",
"X X X \n",
"X O O \n",
"O \n",
"Episode 145, Total Reward: 1\n",
"Average Reward: 0.3586206896551724\n",
"on move: O\n",
" \n",
" \n",
"X \n",
"on move: X\n",
"O \n",
" \n",
"X \n",
"on move: O\n",
"O X \n",
" \n",
"X \n",
"on move: X\n",
"O X \n",
"O \n",
"X \n",
"on move: O\n",
"O X \n",
"O \n",
"X X \n",
"on move: X\n",
"O O X \n",
"O \n",
"X X \n",
"on move: O\n",
"O O X \n",
"O X \n",
"X X \n",
"Episode 146, Total Reward: 1\n",
"Average Reward: 0.363013698630137\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X X \n",
" O \n",
" \n",
"on move: X\n",
"O X X \n",
" O \n",
" \n",
"on move: O\n",
"O X X \n",
" O \n",
" X \n",
"on move: X\n",
"O X X \n",
" O \n",
" O X \n",
"on move: O\n",
"O X X \n",
" X O \n",
" O X \n",
"on move: X\n",
"O X X \n",
"O X O \n",
" O X \n",
"on move: O\n",
"O X X \n",
"O X O \n",
"X O X \n",
"Episode 147, Total Reward: 1\n",
"Average Reward: 0.3673469387755102\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
"O \n",
" \n",
"on move: O\n",
" X \n",
"O \n",
"X \n",
"on move: X\n",
" X \n",
"O O \n",
"X \n",
"on move: O\n",
" X \n",
"O O \n",
"X X \n",
"on move: X\n",
"O X \n",
"O O \n",
"X X \n",
"on move: O\n",
"O X \n",
"O O \n",
"X X X \n",
"Episode 148, Total Reward: 1\n",
"Average Reward: 0.3716216216216216\n",
"on move: O\n",
" \n",
" X \n",
" \n",
"on move: X\n",
" \n",
" X \n",
" O \n",
"on move: O\n",
" \n",
" X X \n",
" O \n",
"on move: X\n",
" \n",
" X X \n",
"O O \n",
"on move: O\n",
" \n",
" X X \n",
"O X O \n",
"on move: X\n",
"O \n",
" X X \n",
"O X O \n",
"on move: O\n",
"O \n",
"X X X \n",
"O X O \n",
"Episode 149, Total Reward: 1\n",
"Average Reward: 0.37583892617449666\n",
"on move: O\n",
" X \n",
" \n",
" \n",
"on move: X\n",
" X \n",
" O \n",
" \n",
"on move: O\n",
" X \n",
" O X \n",
" \n",
"on move: X\n",
" X \n",
" O X \n",
" O \n",
"on move: O\n",
" X \n",
"X O X \n",
" O \n",
"on move: X\n",
" X \n",
"X O X \n",
"O O \n",
"on move: O\n",
" X \n",
"X O X \n",
"O O X \n",
"Episode 150, Total Reward: 1\n",
"Average Reward: 0.38\n"
]
}
],
"source": [
"# Основной цикл обучения (работа с отдельным классом агента)\n",
"\n",
"# Создание среды для игры в крестики-нолики\n",
"environment = TicTacToeEnv()\n",
"\n",
"# Создание агента (играющего крестиками)\n",
"agent = Agent(symbol=1)\n",
"\n",
"num_episodes = 150 # Количество эпизодов (игр) для обучения\n",
"collected_rewards = [] # Список для хранения наград/побед в каждом эпизоде \n",
"\n",
"# Переменная для отслеживания символа и текущего игрока\n",
"oom = 1\n",
"\n",
"for i in range(num_episodes):\n",
" # Сброс среды и начало нового эпизода\n",
" state, _ = environment.reset() \n",
"\n",
" # Общая награда за эпизод\n",
" total_reward = 0\n",
"\n",
" # Флаг завершения игры\n",
" done = False\n",
" om = oom \n",
"\n",
" # Максимум 9 ходов, поскольку поле 3x3 \n",
" for j in range(9): \n",
" moves = environment.move_generator() \n",
"\n",
" # Ходов нет, заканчиваем игру\n",
" if not moves:\n",
" break\n",
"\n",
" \n",
" if len(moves) == 1:\n",
" move = moves[0] # Если остался один ход на основе стратегии\n",
" else:\n",
" move = agent.get_action(moves) # Агент выбирает ход на основе стратегии\n",
"\n",
" # Выполнение хода и обновление состояния игры\n",
" next_state, reward, done, info = environment.step(move)\n",
" total_reward += reward\n",
" state = next_state\n",
"\n",
" # Отображаем текущее состояние игры\n",
" environment.render()\n",
"\n",
" if done:\n",
" break\n",
"\n",
" om = -om # Смена игрока\n",
"\n",
" collected_rewards.append(total_reward)\n",
"\n",
" print(f\"Episode {i+1}, Total Reward: {total_reward}\")\n",
" average_reward = sum(collected_rewards) / len(collected_rewards)\n",
" print(f\"Average Reward: {average_reward}\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "mai",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}