state_action_q_functions.py 文件源码

def __init__(self, n_dim_obs, n_dim_action, n_hidden_channels,
                 n_hidden_layers, nonlinearity=F.relu, last_wscale=1.):
        self.n_input_channels = n_dim_obs + n_dim_action
        self.n_hidden_layers = n_hidden_layers
        self.n_hidden_channels = n_hidden_channels
        self.nonlinearity = nonlinearity
        super().__init__()
        with self.init_scope():
            self.fc = MLP(self.n_input_channels, n_hidden_channels,
                          [self.n_hidden_channels] * self.n_hidden_layers,
                          nonlinearity=nonlinearity,
                          )
            self.lstm = L.LSTM(n_hidden_channels, n_hidden_channels)
            self.out = L.Linear(n_hidden_channels, 1,
                                initialW=LeCunNormal(last_wscale))