train.py 文件源码

def get_experience(seq, action, reward, hist_len, episode_done):
    exp_state = list()
    exp_new_state = list()
    '''
    If we don't have enough images to produce a history
    '''
    if len(seq) < hist_len + 1:
        num_copy = hist_len - (len(seq) - 1)
        for i in range(num_copy):
            exp_state.append(seq[0])
        for i in range(len(seq) - 1):
            exp_state.append(seq[i])

        num_copy = hist_len - len(seq)
        for i in range(num_copy):
            exp_new_state.append(seq[0])
        for i in range(len(seq)):
            exp_new_state.append(seq[i])
    else:
        exp_state = seq[-hist_len - 1 : -1]
        exp_new_state = seq[-hist_len:]
    exp = Experience(state=np.moveaxis(exp_state, 0, -1), action=action, reward=reward, new_state=np.moveaxis(exp_new_state, 0, -1), game_over=episode_done)
    return exp