train.py 文件源码

def __init__(self, action_space, screen=(84, 84), n_step=8, discount=0.99):
        from keras.optimizers import RMSprop
        # -----
        self.screen = screen
        self.input_depth = 1
        self.past_range = 3
        self.observation_shape = (self.input_depth * self.past_range,) + self.screen

        self.action_value = build_network(self.observation_shape, action_space.n)
        self.action_value.compile(optimizer=RMSprop(clipnorm=1.), loss='mse')  # clipnorm=1.

        self.action_space = action_space
        self.observations = np.zeros(self.observation_shape)
        self.last_observations = np.zeros_like(self.observations)
        # -----
        self.n_step_observations = deque(maxlen=n_step)
        self.n_step_actions = deque(maxlen=n_step)
        self.n_step_rewards = deque(maxlen=n_step)
        self.n_step = n_step
        self.discount = discount
        self.counter = 0