critic_network.py 文件源码

def create_q_network(self,state_dim,action_dim):
        # the layer size could be changed
        layer1_size = LAYER1_SIZE
        layer2_size = LAYER2_SIZE

        state_input = tf.placeholder("float",[None,state_dim])
        action_input = tf.placeholder("float",[None,action_dim])

        W1 = self.variable([state_dim,layer1_size],state_dim)
        b1 = self.variable([layer1_size],state_dim)
        W2 = self.variable([layer1_size,layer2_size],layer1_size+action_dim)
        W2_action = self.variable([action_dim,layer2_size],layer1_size+action_dim)
        b2 = self.variable([layer2_size],layer1_size+action_dim)
        W3 = tf.Variable(tf.random_uniform([layer2_size,1],-3e-3,3e-3))
        b3 = tf.Variable(tf.random_uniform([1],-3e-3,3e-3))

        layer1 = tf.nn.relu(tf.matmul(state_input,W1) + b1)
        layer2 = tf.nn.relu(tf.matmul(layer1,W2) + tf.matmul(action_input,W2_action) + b2)
        q_value_output = tf.identity(tf.matmul(layer2,W3) + b3)

        return state_input,action_input,q_value_output,[W1,b1,W2,W2_action,b2,W3,b3]