q_net.py 文件源码

def __init__(self, use_gpu, enable_controller, dim):
        self.use_gpu = use_gpu
        self.num_of_actions = len(enable_controller)
        self.enable_controller = enable_controller
        self.dim = dim

        print("Initializing Q-Network...")

        hidden_dim = 256
        self.model = FunctionSet(
            l4=F.Linear(self.dim*self.hist_size, hidden_dim, wscale=np.sqrt(2)),
            q_value=F.Linear(hidden_dim, self.num_of_actions,
                             initialW=np.zeros((self.num_of_actions, hidden_dim),
                                               dtype=np.float32))
        )
        if self.use_gpu >= 0:
            self.model.to_gpu()

        self.model_target = copy.deepcopy(self.model)

        self.optimizer = optimizers.RMSpropGraves(lr=0.00025, alpha=0.95, momentum=0.95, eps=0.0001)
        self.optimizer.setup(self.model.collect_parameters())

        # History Data :  D=[s, a, r, s_dash, end_episode_flag]
        self.d = [np.zeros((self.data_size, self.hist_size, self.dim), dtype=np.uint8),
                  np.zeros(self.data_size, dtype=np.uint8),
                  np.zeros((self.data_size, 1), dtype=np.int8),
                  np.zeros((self.data_size, self.hist_size, self.dim), dtype=np.uint8),
                  np.zeros((self.data_size, 1), dtype=np.bool)]