当前位置: 首页>>代码示例>>Python>>正文


Python deepq.wrap_atari_dqn方法代码示例

本文整理汇总了Python中baselines.deepq.wrap_atari_dqn方法的典型用法代码示例。如果您正苦于以下问题:Python deepq.wrap_atari_dqn方法的具体用法?Python deepq.wrap_atari_dqn怎么用?Python deepq.wrap_atari_dqn使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在baselines.deepq的用法示例。


在下文中一共展示了deepq.wrap_atari_dqn方法的8个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: main

# 需要导入模块: from baselines import deepq [as 别名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 别名]
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() 
开发者ID:hiwonjoon,项目名称:ICML2019-TREX,代码行数:27,代码来源:train_pong.py

示例2: main

# 需要导入模块: from baselines import deepq [as 别名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 别名]
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) 
开发者ID:hiwonjoon,项目名称:ICML2019-TREX,代码行数:22,代码来源:enjoy_pong.py

示例3: main

# 需要导入模块: from baselines import deepq [as 别名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 别名]
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() 
开发者ID:Hwhitetooth,项目名称:lirpg,代码行数:36,代码来源:run_atari.py

示例4: main

# 需要导入模块: from baselines import deepq [as 别名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 别名]
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) 
开发者ID:Hwhitetooth,项目名称:lirpg,代码行数:15,代码来源:enjoy_pong.py

示例5: main

# 需要导入模块: from baselines import deepq [as 别名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 别名]
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() 
开发者ID:MaxSobolMark,项目名称:HardRLWithYoutube,代码行数:42,代码来源:run_atari.py

示例6: main

# 需要导入模块: from baselines import deepq [as 别名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 别名]
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() 
开发者ID:flyyufelix,项目名称:sonic_contest,代码行数:39,代码来源:run_atari.py

示例7: main

# 需要导入模块: from baselines import deepq [as 别名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 别名]
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() 
开发者ID:ArztSamuel,项目名称:DRL_DeliveryDuel,代码行数:48,代码来源:run_atari.py

示例8: main

# 需要导入模块: from baselines import deepq [as 别名]
# 或者: from baselines.deepq import wrap_atari_dqn [as 别名]
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() 
开发者ID:junhyukoh,项目名称:self-imitation-learning,代码行数:44,代码来源:run_atari.py


注:本文中的baselines.deepq.wrap_atari_dqn方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。