ConnectXで強化学習したい

result = state['board'][:]
でboardがないとエラーが起こるのでこちらを参考にして下さい。

どうやらstate[0]とstate[1]を切り替えなければならないそうです。

def play_game(env, TrainNet, TargetNet, epsilon, copy_step):
    rewards = 0
    iter = 0
    done = False
    observations = env.reset()

    while not done:
        if env.state[0].status == 'ACTIVE':
            player_id = 0
        elif env.state[1].status == 'ACTIVE':
            player_id = 1
        observations = env.state[player_id].observation
        # Using epsilon-greedy to get an action
        action = TrainNet.get_action(observations, epsilon)

        # Caching the information of current state
        prev_observations = observations

        # Take action
        observations, reward, done, _ = env.step(action)

        # Apply new rules
        if done:
            TrainNet.train_loss /= iter
            if reward == 1: # Won
                reward = 20
            elif reward == 0: # Lost
                reward = -20
            else: # Draw
                reward = 10
        else:
#             reward = -0.05 # Try to prevent the agent from taking a long move

            # Try to promote the agent to "struggle" when playing against negamax agent
            # as Magolor's (@magolor) idea
            reward = 0.5

        rewards += reward

        # Adding experience into buffer
        exp = {'s': prev_observations, 'a': action, 'r': reward, 's2': observations, 'done': done}
        TrainNet.add_experience(exp)

        # Train the training model by using experiences in buffer and the target model
        TrainNet.train(TargetNet)
        iter += 1
        if iter % copy_step == 0:
            # Update the weights of the target model when reaching enough "copy step"
            TargetNet.copy_weights(TrainNet)
    return rewards