critic_net.py 文件源码

def create_critic_net(self, num_states=4, num_actions=1):
        N_HIDDEN_1 = 400
        N_HIDDEN_2 = 300
        critic_state_in = tf.placeholder("float",[None,num_states])
        critic_action_in = tf.placeholder("float",[None,num_actions])    

        W1_c = tf.Variable(tf.random_uniform([num_states,N_HIDDEN_1],-1/math.sqrt(num_states),1/math.sqrt(num_states)))
        B1_c = tf.Variable(tf.random_uniform([N_HIDDEN_1],-1/math.sqrt(num_states),1/math.sqrt(num_states)))
        W2_c = tf.Variable(tf.random_uniform([N_HIDDEN_1,N_HIDDEN_2],-1/math.sqrt(N_HIDDEN_1+num_actions),1/math.sqrt(N_HIDDEN_1+num_actions)))    
        W2_action_c = tf.Variable(tf.random_uniform([num_actions,N_HIDDEN_2],-1/math.sqrt(N_HIDDEN_1+num_actions),1/math.sqrt(N_HIDDEN_1+num_actions)))    
        B2_c= tf.Variable(tf.random_uniform([N_HIDDEN_2],-1/math.sqrt(N_HIDDEN_1+num_actions),1/math.sqrt(N_HIDDEN_1+num_actions))) 
        W3_c= tf.Variable(tf.random_uniform([N_HIDDEN_2,1],-0.003,0.003))
        B3_c= tf.Variable(tf.random_uniform([1],-0.003,0.003))

        H1_c=tf.nn.softplus(tf.matmul(critic_state_in,W1_c)+B1_c)
        H2_c=tf.nn.tanh(tf.matmul(H1_c,W2_c)+tf.matmul(critic_action_in,W2_action_c)+B2_c)

        critic_q_model=tf.matmul(H2_c,W3_c)+B3_c


        return W1_c, B1_c, W2_c, W2_action_c, B2_c, W3_c, B3_c, critic_q_model, critic_state_in, critic_action_in