16a31e2c9fedc654e9117b42b8144adf1d0e4900,examples/reinforcement_learning/tutorial_A3C.py,,,#,259

Before Change

        plt.plot(GLOBAL_RUNNING_R)
        plt.xlabel("episode")
        plt.ylabel("global running reward")
        plt.savefig("a3c.png")
        plt.show()

        GLOBAL_AC.save_ckpt()

After Change

                if d:
                    break
            print(
                "Testing  | Episode: {}/{}  | Episode Reward: {:.4f}  | Running Time: {:.4f}".format(
                    episode + 1, TEST_EPISODES, episode_reward,
                    time.time() - T0))

Instances