8b68349d43621619fe799ab4afc21da7f1fb2515,examples/reinforcement_learning/tutorial_PPO.py,,,#,233

Before Change

        all_ep_r.append(ep_r)
    else:
        all_ep_r.append(all_ep_r[-1] * 0.9 + ep_r * 0.1)
    print(
        "Ep: %i" % ep,
        "|Ep_r: %i" % ep_r,
        ("|Lam: %.4f" % METHOD["lam"]) if METHOD["name"] == "kl_pen" else "",
    )

    plt.ion()
    plt.cla()
    plt.title("PPO")

After Change

    // reproducible
    env.seed(RANDOMSEED)
    np.random.seed(RANDOMSEED)
    tf.random.set_seed(RANDOMSEED)

    ppo = PPO()

Instances