a6652b0c1997bb47dd502bf674e0b3b9b2d09d23,examples/reinforcement_learning/tutorial_bipedalwalker_a3c_continuous_action.py,,,#,254

Before Change

            workers.append(Worker(i_name, GLOBAL_AC))

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

    // start TF threading
    worker_threads = []
    for worker in workers:

After Change

        s = env.reset()
        rall = 0
        while True:
            env.render()
            s = s.astype("float32") // double to float
            a = GLOBAL_AC.choose_action(s)
            s, r, d, _ = env.step(a)
            rall += r

Instances