ccbd460791dc0229302fcfda37ab7c4f3ce9e08a,Reinforcement_learning_TUT/10_A3C/A3C_discrete_action.py,,,#,166

Before Change

        for i in range(N_WORKERS):
            i_name = "W_%i" % i   // worker name
            workers.append(
                Worker(
                    gym.make(GAME).unwrapped, i_name, N_S, N_A, sess,
                    OPT_A, OPT_C, globalAC.a_params, globalAC.c_params
                ))

    coord = tf.train.Coordinator()
    sess.run(tf.global_variables_initializer())

After Change

        COUNT_GLOBAL_EP = tf.assign(GLOBAL_EP, tf.add(GLOBAL_EP, tf.constant(1), name="step_ep"))
        OPT_A = tf.train.RMSPropOptimizer(LR_A, name="RMSPropA")
        OPT_C = tf.train.RMSPropOptimizer(LR_C, name="RMSPropC")
        GLOBAL_AC = ACNet(GLOBAL_NET_SCOPE)  // we only need its params
        workers = []
        // Create worker
        for i in range(N_WORKERS):
            i_name = "W_%i" % i   // worker name
            workers.append(Worker(i_name, GLOBAL_AC))

    COORD = tf.train.Coordinator()
    SESS.run(tf.global_variables_initializer())

Instances