gaussian_policy.py 文件源码

def __init__(self, n_input_channels, action_size,
                 n_hidden_layers=0, n_hidden_channels=None,
                 min_action=None, max_action=None, bound_mean=False,
                 var_type='spherical',
                 nonlinearity=F.relu, mean_wscale=1):

        self.n_input_channels = n_input_channels
        self.action_size = action_size
        self.n_hidden_layers = n_hidden_layers
        self.n_hidden_channels = n_hidden_channels
        self.min_action = min_action
        self.max_action = max_action
        self.bound_mean = bound_mean
        self.nonlinearity = nonlinearity
        var_size = {'spherical': 1, 'diagonal': action_size}[var_type]

        layers = []
        layers.append(L.Linear(n_input_channels, n_hidden_channels))
        for _ in range(n_hidden_layers - 1):
            layers.append(self.nonlinearity)
            layers.append(L.Linear(n_hidden_channels, n_hidden_channels))
        layers.append(self.nonlinearity)
        # The last layer is used to compute the mean
        layers.append(
            L.Linear(n_hidden_channels, action_size,
                     initialW=LeCunNormal(mean_wscale)))

        if self.bound_mean:
            layers.append(lambda x: bound_by_tanh(
                x, self.min_action, self.max_action))

        super().__init__()
        with self.init_scope():
            self.hidden_layers = links.Sequence(*layers)
            self.var_param = chainer.Parameter(
                initializer=0.0, shape=(var_size,))