示例#1
0
 def _init_weights(self):
     self.apply(init_weights)
     self.fc4.weight.data = normalized_columns_initializer(
         self.fc4.weight.data, 0.0001)
     self.fc4.bias.data.fill_(0)
     self.fc5.weight.data = normalized_columns_initializer(
         self.fc5.weight.data, 0.0001)
     self.fc5.bias.data.fill_(0)
示例#2
0
    def _init_weights(self):
        self.apply(init_weights)
        self.policy_5.weight.data = normalized_columns_initializer(self.policy_5.weight.data, 0.01)
        self.policy_5.bias.data.fill_(0)
        self.value_5.weight.data = normalized_columns_initializer(self.value_5.weight.data, 1.0)
        self.value_5.bias.data.fill_(0)

        self.lstm.bias_ih.data.fill_(0)
        self.lstm.bias_hh.data.fill_(0)
示例#3
0
    def _init_weights(self):
        self.apply(init_weights)
        self.actor_5.weight.data = normalized_columns_initializer(
            self.actor_5.weight.data, 0.01)
        self.actor_5.bias.data.fill_(0)
        self.critic_5.weight.data = normalized_columns_initializer(
            self.critic_5.weight.data, 1.0)
        self.critic_5.bias.data.fill_(0)

        self.lstm.bias_ih.data.fill_(0)
        self.lstm.bias_hh.data.fill_(0)
示例#4
0
 def _init_weights(self):
     self.apply(init_weights)
     self.fc1.weight.data = normalized_columns_initializer(
         self.fc1.weight.data, 0.01)
     self.fc1.bias.data.fill_(0)
     self.fc2.weight.data = normalized_columns_initializer(
         self.fc2.weight.data, 0.01)
     self.fc2.bias.data.fill_(0)
     self.fc3.weight.data = normalized_columns_initializer(
         self.fc3.weight.data, 0.01)
     self.fc3.bias.data.fill_(0)
     self.policy_7.weight.data = normalized_columns_initializer(
         self.policy_7.weight.data, 0.01)
     self.policy_7.bias.data.fill_(0)
     self.value_8.weight.data = normalized_columns_initializer(
         self.value_8.weight.data, 1.0)
     self.value_8.bias.data.fill_(0)
示例#5
0
    def _init_weights(self):
        self.apply(init_weights)

        self.inverse_FC1.weight.data = normalized_columns_initializer(self.inverse_FC1.weight.data, 0.01)
        self.inverse_FC1.bias.data.fill_(0)
        self.inverse_FC2.weight.data = normalized_columns_initializer(self.inverse_FC2.weight.data, 1.0)
        self.inverse_FC2.bias.data.fill_(0)

        self.forward_FC1.weight.data = normalized_columns_initializer(self.forward_FC1.weight.data, 0.01)
        self.forward_FC1.bias.data.fill_(0)
        self.forward_FC2.weight.data = normalized_columns_initializer(self.forward_FC2.weight.data, 1.0)
        self.forward_FC2.bias.data.fill_(0)

        self.actor_linear.weight.data = normalized_columns_initializer(self.actor_linear.weight.data, 0.01)
        self.actor_linear.bias.data.fill_(0)
        self.critic_linear.weight.data = normalized_columns_initializer(self.critic_linear.weight.data, 1.0)
        self.critic_linear.bias.data.fill_(0)

        self.lstm.bias_ih.data.fill_(0)
        self.lstm.bias_hh.data.fill_(0)