Python deepq.wrap_atari_dqn方法代碼示例

本文整理匯總了Python中baselines.deepq.wrap_atari_dqn方法的典型用法代碼示例。如果您正苦於以下問題：Python deepq.wrap_atari_dqn方法的具體用法？Python deepq.wrap_atari_dqn怎麽用？Python deepq.wrap_atari_dqn使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類baselines.deepq的用法示例。

在下文中一共展示了deepq.wrap_atari_dqn方法的8個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: main

# 需要導入模塊: from baselines import deepq [as 別名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 別名]
def main():
    logger.configure()
    env = make_atari('PongNoFrameskip-v4')
    env = bench.Monitor(env, logger.get_dir())
    env = deepq.wrap_atari_dqn(env)

    model = deepq.learn(
        env,
        "conv_only",
        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
        hiddens=[256],
        dueling=True,
        lr=1e-4,
        total_timesteps=int(1e7),
        buffer_size=10000,
        exploration_fraction=0.1,
        exploration_final_eps=0.01,
        train_freq=4,
        learning_starts=10000,
        target_network_update_freq=1000,
        gamma=0.99,
    )

    model.save('pong_model.pkl')
    env.close()

開發者ID:hiwonjoon，項目名稱:ICML2019-TREX，代碼行數:27，代碼來源:train_pong.py

示例2: main

# 需要導入模塊: from baselines import deepq [as 別名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 別名]
def main():
    env = gym.make("PongNoFrameskip-v4")
    env = deepq.wrap_atari_dqn(env)
    model = deepq.learn(
        env,
        "conv_only",
        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
        hiddens=[256],
        dueling=True,
        total_timesteps=0
    )

    while True:
        obs, done = env.reset(), False
        episode_rew = 0
        while not done:
            env.render()
            obs, rew, done, _ = env.step(model(obs[None])[0])
            episode_rew += rew
        print("Episode reward", episode_rew)

開發者ID:hiwonjoon，項目名稱:ICML2019-TREX，代碼行數:22，代碼來源:enjoy_pong.py

示例3: main

# 需要導入模塊: from baselines import deepq [as 別名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 別名]
def main():
    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument('--env', help='environment ID', default='BreakoutNoFrameskip-v4')
    parser.add_argument('--seed', help='RNG seed', type=int, default=0)
    parser.add_argument('--prioritized', type=int, default=1)
    parser.add_argument('--dueling', type=int, default=1)
    parser.add_argument('--num-timesteps', type=int, default=int(10e6))
    args = parser.parse_args()
    logger.configure()
    set_global_seeds(args.seed)
    env = make_atari(args.env)
    env = bench.Monitor(env, logger.get_dir())
    env = deepq.wrap_atari_dqn(env)
    model = deepq.models.cnn_to_mlp(
        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
        hiddens=[256],
        dueling=bool(args.dueling),
    )
    act = deepq.learn(
        env,
        q_func=model,
        lr=1e-4,
        max_timesteps=args.num_timesteps,
        buffer_size=10000,
        exploration_fraction=0.1,
        exploration_final_eps=0.01,
        train_freq=4,
        learning_starts=10000,
        target_network_update_freq=1000,
        gamma=0.99,
        prioritized_replay=bool(args.prioritized)
    )
    # act.save("pong_model.pkl") XXX
    env.close()

開發者ID:Hwhitetooth，項目名稱:lirpg，代碼行數:36，代碼來源:run_atari.py

示例4: main

# 需要導入模塊: from baselines import deepq [as 別名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 別名]
def main():
    env = gym.make("PongNoFrameskip-v4")
    env = deepq.wrap_atari_dqn(env)
    act = deepq.load("pong_model.pkl")

    while True:
        obs, done = env.reset(), False
        episode_rew = 0
        while not done:
            env.render()
            obs, rew, done, _ = env.step(act(obs[None])[0])
            episode_rew += rew
        print("Episode reward", episode_rew)

開發者ID:Hwhitetooth，項目名稱:lirpg，代碼行數:15，代碼來源:enjoy_pong.py

示例5: main

# 需要導入模塊: from baselines import deepq [as 別名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 別名]
def main():
    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument('--env', help='environment ID', default='BreakoutNoFrameskip-v4')
    parser.add_argument('--seed', help='RNG seed', type=int, default=0)
    parser.add_argument('--prioritized', type=int, default=1)
    parser.add_argument('--prioritized-replay-alpha', type=float, default=0.6)
    parser.add_argument('--dueling', type=int, default=1)
    parser.add_argument('--num-timesteps', type=int, default=int(10e6))
    parser.add_argument('--checkpoint-freq', type=int, default=10000)
    parser.add_argument('--checkpoint-path', type=str, default=None)

    args = parser.parse_args()
    logger.configure()
    set_global_seeds(args.seed)
    env = make_atari(args.env)
    env = bench.Monitor(env, logger.get_dir())
    env = deepq.wrap_atari_dqn(env)

    deepq.learn(
        env,
        "conv_only",
        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
        hiddens=[256],
        dueling=bool(args.dueling),
        lr=1e-4,
        total_timesteps=args.num_timesteps,
        buffer_size=10000,
        exploration_fraction=0.1,
        exploration_final_eps=0.01,
        train_freq=4,
        learning_starts=10000,
        target_network_update_freq=1000,
        gamma=0.99,
        prioritized_replay=bool(args.prioritized),
        prioritized_replay_alpha=args.prioritized_replay_alpha,
        checkpoint_freq=args.checkpoint_freq,
        checkpoint_path=args.checkpoint_path,
    )

    env.close()

開發者ID:MaxSobolMark，項目名稱:HardRLWithYoutube，代碼行數:42，代碼來源:run_atari.py

示例6: main

# 需要導入模塊: from baselines import deepq [as 別名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 別名]
def main():
    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument('--env', help='environment ID', default='BreakoutNoFrameskip-v4')
    parser.add_argument('--seed', help='RNG seed', type=int, default=0)
    parser.add_argument('--prioritized', type=int, default=1)
    parser.add_argument('--prioritized-replay-alpha', type=float, default=0.6)
    parser.add_argument('--dueling', type=int, default=1)
    parser.add_argument('--num-timesteps', type=int, default=int(10e6))
    args = parser.parse_args()
    logger.configure()
    set_global_seeds(args.seed)
    env = make_atari(args.env)
    env = bench.Monitor(env, logger.get_dir())
    env = deepq.wrap_atari_dqn(env)
    model = deepq.models.cnn_to_mlp(
        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
        hiddens=[256],
        dueling=bool(args.dueling),
    )

    deepq.learn(
        env,
        q_func=model,
        lr=1e-4,
        max_timesteps=args.num_timesteps,
        buffer_size=10000,
        exploration_fraction=0.1,
        exploration_final_eps=0.01,
        train_freq=4,
        learning_starts=10000,
        target_network_update_freq=1000,
        gamma=0.99,
        prioritized_replay=bool(args.prioritized),
        prioritized_replay_alpha=args.prioritized_replay_alpha
    )

    env.close()

開發者ID:flyyufelix，項目名稱:sonic_contest，代碼行數:39，代碼來源:run_atari.py

示例7: main

# 需要導入模塊: from baselines import deepq [as 別名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 別名]
def main():
    global abort_training
    global q_pressed
    
    abort_training = False
    q_pressed = False
    
    listener = keyboard.Listener(on_press=on_press, on_release=on_release)
    listener.start()
    
    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument('--env', help='environment ID', default='BreakoutNoFrameskip-v4')
    parser.add_argument('--seed', help='RNG seed', type=int, default=0)
    parser.add_argument('--prioritized', type=int, default=1)
    parser.add_argument('--dueling', type=int, default=1)
    parser.add_argument('--num-timesteps', type=int, default=int(10e6))
    args = parser.parse_args()
    logger.configure()
    set_global_seeds(args.seed)
    env = make_atari(args.env)
    env = bench.Monitor(env, logger.get_dir())
    env = deepq.wrap_atari_dqn(env)
    model = deepq.models.cnn_to_mlp(
        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
        hiddens=[256],
        dueling=bool(args.dueling),
    )
    act = deepq.learn(
        env,
        q_func=model,
        lr=1e-4,
        max_timesteps=args.num_timesteps,
        buffer_size=10000,
        exploration_fraction=0.1,
        exploration_final_eps=0.01,
        train_freq=4,
        learning_starts=10000,
        target_network_update_freq=1000,
        gamma=0.99,
        print_freq=1,
        prioritized_replay=bool(args.prioritized),
        callback=callback
    )    
    print("Saving model to pong_model.pkl")
    act.save("pong_model.pkl")
    env.close()

開發者ID:ArztSamuel，項目名稱:DRL_DeliveryDuel，代碼行數:48，代碼來源:run_atari.py

示例8: main

# 需要導入模塊: from baselines import deepq [as 別名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 別名]
def main():
    parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument('--env', help='environment ID', default='BreakoutNoFrameskip-v4')
    parser.add_argument('--seed', help='RNG seed', type=int, default=0)
    parser.add_argument('--prioritized', type=int, default=1)
    parser.add_argument('--prioritized-replay-alpha', type=float, default=0.6)
    parser.add_argument('--dueling', type=int, default=1)
    parser.add_argument('--num-timesteps', type=int, default=int(10e6))
    parser.add_argument('--checkpoint-freq', type=int, default=10000)
    parser.add_argument('--checkpoint-path', type=str, default=None)

    args = parser.parse_args()
    logger.configure()
    set_global_seeds(args.seed)
    env = make_atari(args.env)
    env = bench.Monitor(env, logger.get_dir())
    env = deepq.wrap_atari_dqn(env)
    model = deepq.models.cnn_to_mlp(
        convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
        hiddens=[256],
        dueling=bool(args.dueling),
    )

    deepq.learn(
        env,
        q_func=model,
        lr=1e-4,
        max_timesteps=args.num_timesteps,
        buffer_size=10000,
        exploration_fraction=0.1,
        exploration_final_eps=0.01,
        train_freq=4,
        learning_starts=10000,
        target_network_update_freq=1000,
        gamma=0.99,
        prioritized_replay=bool(args.prioritized),
        prioritized_replay_alpha=args.prioritized_replay_alpha,
        checkpoint_freq=args.checkpoint_freq,
        checkpoint_path=args.checkpoint_path,
    )

    env.close()

開發者ID:junhyukoh，項目名稱:self-imitation-learning，代碼行數:44，代碼來源:run_atari.py

注：本文中的baselines.deepq.wrap_atari_dqn方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。