deterministic_policy.py 文件源码

def __init__(self, n_input_channels, n_hidden_layers,
                 n_hidden_channels, action_size,
                 min_action=None, max_action=None, bound_action=True,
                 nonlinearity=F.relu,
                 last_wscale=1.):
        self.n_input_channels = n_input_channels
        self.n_hidden_layers = n_hidden_layers
        self.n_hidden_channels = n_hidden_channels
        self.action_size = action_size
        self.min_action = min_action
        self.max_action = max_action
        self.bound_action = bound_action

        if self.bound_action:
            def action_filter(x):
                return bound_by_tanh(
                    x, self.min_action, self.max_action)
        else:
            action_filter = None

        model = chainer.Chain(
            fc=MLP(self.n_input_channels,
                   n_hidden_channels,
                   (self.n_hidden_channels,) * self.n_hidden_layers,
                   nonlinearity=nonlinearity,
                   ),
            lstm=L.LSTM(n_hidden_channels, n_hidden_channels),
            out=L.Linear(n_hidden_channels, action_size,
                         initialW=LeCunNormal(last_wscale)),
        )

        def model_call(model, x):
            h = nonlinearity(model.fc(x))
            h = model.lstm(h)
            h = model.out(h)
            return h

        super().__init__(
            model=model,
            model_call=model_call,
            action_filter=action_filter)