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.):
        assert n_hidden_layers >= 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():
            # No need to pass nonlinearity to obs_mlp because it has no
            # hidden layers
            self.obs_mlp = MLP(in_size=n_dim_obs, out_size=n_hidden_channels,
                               hidden_sizes=[])
            self.mlp = MLP(in_size=n_hidden_channels + n_dim_action,
                           out_size=1,
                           hidden_sizes=([self.n_hidden_channels] *
                                         (self.n_hidden_layers - 1)),
                           nonlinearity=nonlinearity,
                           last_wscale=last_wscale,
                           )

        self.output = self.mlp.output