train_a3c_ale.py 文件源码

def __init__(self, n_actions):
        self.head = links.NIPSDQNHead()
        self.pi = policy.FCSoftmaxPolicy(
            self.head.n_output_channels, n_actions)
        self.v = v_function.FCVFunction(self.head.n_output_channels)
        self.lstm = L.LSTM(self.head.n_output_channels,
                           self.head.n_output_channels)
        super().__init__(self.head, self.lstm, self.pi, self.v)