6ca2a6359dc1374bfb211da8680f3d5f319cdaa5,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

            env.render()
            s = s.astype("float32")  // double to float
            a = GLOBAL_AC.choose_action(s)
            s, r, d, _ = env.step(a)
            rall += r
            if d:
                print("reward", rall)
                break

Instances