softmax_policy.py 文件源码

def __init__(self, n_input_channels, n_actions,
                 n_hidden_layers=0, n_hidden_channels=None,
                 beta=1.0, nonlinearity=F.relu,
                 last_wscale=1.0,
                 min_prob=0.0):
        self.n_input_channels = n_input_channels
        self.n_actions = n_actions
        self.n_hidden_layers = n_hidden_layers
        self.n_hidden_channels = n_hidden_channels
        self.beta = beta

        super().__init__(
            model=MLP(n_input_channels,
                      n_actions,
                      (n_hidden_channels,) * n_hidden_layers,
                      nonlinearity=nonlinearity,
                      last_wscale=last_wscale),
            beta=self.beta,
            min_prob=min_prob)