当前位置: 首页>>代码示例>>Python>>正文


Python models.Critic方法代码示例

本文整理汇总了Python中baselines.ddpg.models.Critic方法的典型用法代码示例。如果您正苦于以下问题:Python models.Critic方法的具体用法?Python models.Critic怎么用?Python models.Critic使用的例子?那么恭喜您, 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.ddpg.models的用法示例。


在下文中一共展示了models.Critic方法的3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: run

# 需要导入模块: from baselines.ddpg import models [as 别名]
# 或者: from baselines.ddpg.models import Critic [as 别名]
def run(env_id, seed, noise_type, layer_norm, evaluation, **kwargs):
    # Configure things.
    rank = MPI.COMM_WORLD.Get_rank()
    if rank != 0:
        logger.set_level(logger.DISABLED)

    # Create envs.
    env = gym.make(env_id)
    env = bench.Monitor(env, logger.get_dir() and os.path.join(logger.get_dir(), str(rank)))

    if evaluation and rank==0:
        eval_env = gym.make(env_id)
        eval_env = bench.Monitor(eval_env, os.path.join(logger.get_dir(), 'gym_eval'))
        env = bench.Monitor(env, None)
    else:
        eval_env = None

    # Parse noise_type
    action_noise = None
    param_noise = None
    nb_actions = env.action_space.shape[-1]
    for current_noise_type in noise_type.split(','):
        current_noise_type = current_noise_type.strip()
        if current_noise_type == 'none':
            pass
        elif 'adaptive-param' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            param_noise = AdaptiveParamNoiseSpec(initial_stddev=float(stddev), desired_action_stddev=float(stddev))
        elif 'normal' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            action_noise = NormalActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions))
        elif 'ou' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            action_noise = OrnsteinUhlenbeckActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions))
        else:
            raise RuntimeError('unknown noise type "{}"'.format(current_noise_type))

    # Configure components.
    memory = Memory(limit=int(1e6), action_shape=env.action_space.shape, observation_shape=env.observation_space.shape)
    critic = Critic(layer_norm=layer_norm)
    actor = Actor(nb_actions, layer_norm=layer_norm)

    # Seed everything to make things reproducible.
    seed = seed + 1000000 * rank
    logger.info('rank {}: seed={}, logdir={}'.format(rank, seed, logger.get_dir()))
    tf.reset_default_graph()
    set_global_seeds(seed)
    env.seed(seed)
    if eval_env is not None:
        eval_env.seed(seed)

    # Disable logging for rank != 0 to avoid noise.
    if rank == 0:
        start_time = time.time()
    training.train(env=env, eval_env=eval_env, param_noise=param_noise,
        action_noise=action_noise, actor=actor, critic=critic, memory=memory, **kwargs)
    env.close()
    if eval_env is not None:
        eval_env.close()
    if rank == 0:
        logger.info('total runtime: {}s'.format(time.time() - start_time)) 
开发者ID:Hwhitetooth,项目名称:lirpg,代码行数:63,代码来源:main.py

示例2: run

# 需要导入模块: from baselines.ddpg import models [as 别名]
# 或者: from baselines.ddpg.models import Critic [as 别名]
def run(seed, noise_type, layer_norm, evaluation, **kwargs):
    # Configure things.
    rank = MPI.COMM_WORLD.Get_rank()
    if rank != 0:
        logger.set_level(logger.DISABLED)

    # Create envs.
    env = gymify_osim_env(Arm3dEnv(visualize = True))
    env = bench.Monitor(env, logger.get_dir() and os.path.join(logger.get_dir(), str(rank)))

    if evaluation and rank==0:
        eval_env = gymify_osim_env(Arm3dEnv(visualize = True))
        eval_env = bench.Monitor(eval_env, os.path.join(logger.get_dir(), 'gym_eval'))
        env = bench.Monitor(env, None)
    else:
        eval_env = None

    # Parse noise_type
    action_noise = None
    param_noise = None
    nb_actions = env.action_space.shape[-1]
    for current_noise_type in noise_type.split(','):
        current_noise_type = current_noise_type.strip()
        if current_noise_type == 'none':
            pass
        elif 'adaptive-param' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            param_noise = AdaptiveParamNoiseSpec(initial_stddev=float(stddev), desired_action_stddev=float(stddev))
        elif 'normal' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            action_noise = NormalActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions))
        elif 'ou' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            action_noise = OrnsteinUhlenbeckActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions))
        else:
            raise RuntimeError('unknown noise type "{}"'.format(current_noise_type))

    # Configure components.
    memory = Memory(limit=int(1e6), action_shape=env.action_space.shape, observation_shape=env.observation_space.shape)
    critic = Critic(layer_norm=layer_norm)
    actor = Actor(nb_actions, layer_norm=layer_norm)

    # Seed everything to make things reproducible.
    seed = seed + 1000000 * rank
    logger.info('rank {}: seed={}, logdir={}'.format(rank, seed, logger.get_dir()))
    tf.reset_default_graph()
    set_global_seeds(seed)
    env.seed(seed)
    if eval_env is not None:
        eval_env.seed(seed)

    # Disable logging for rank != 0 to avoid noise.
    if rank == 0:
        start_time = time.time()
    training.train(env=env, eval_env=eval_env, param_noise=param_noise,
        action_noise=action_noise, actor=actor, critic=critic, memory=memory, **kwargs)
    env.close()
    if eval_env is not None:
        eval_env.close()
    if rank == 0:
        logger.info('total runtime: {}s'.format(time.time() - start_time)) 
开发者ID:stanfordnmbl,项目名称:osim-rl,代码行数:63,代码来源:train.arm.py

示例3: run

# 需要导入模块: from baselines.ddpg import models [as 别名]
# 或者: from baselines.ddpg.models import Critic [as 别名]
def run(seed, noise_type, layer_norm, evaluation, **kwargs):
    # Configure things.
    rank = MPI.COMM_WORLD.Get_rank()
    if rank != 0:
        logger.set_level(logger.DISABLED)

    # Create envs.
    env = gymify_osim_env(L2RunEnv(visualize = True))
    env = bench.Monitor(env, logger.get_dir() and os.path.join(logger.get_dir(), str(rank)))

    if evaluation and rank==0:
        eval_env = gymify_osim_env(L2RunEnv(visualize = True))
        eval_env = bench.Monitor(eval_env, os.path.join(logger.get_dir(), 'gym_eval'))
        env = bench.Monitor(env, None)
    else:
        eval_env = None

    # Parse noise_type
    action_noise = None
    param_noise = None
    nb_actions = env.action_space.shape[-1]
    for current_noise_type in noise_type.split(','):
        current_noise_type = current_noise_type.strip()
        if current_noise_type == 'none':
            pass
        elif 'adaptive-param' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            param_noise = AdaptiveParamNoiseSpec(initial_stddev=float(stddev), desired_action_stddev=float(stddev))
        elif 'normal' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            action_noise = NormalActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions))
        elif 'ou' in current_noise_type:
            _, stddev = current_noise_type.split('_')
            action_noise = OrnsteinUhlenbeckActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions))
        else:
            raise RuntimeError('unknown noise type "{}"'.format(current_noise_type))

    # Configure components.
    memory = Memory(limit=int(1e6), action_shape=env.action_space.shape, observation_shape=env.observation_space.shape)
    critic = Critic(layer_norm=layer_norm)
    actor = Actor(nb_actions, layer_norm=layer_norm)

    # Seed everything to make things reproducible.
    seed = seed + 1000000 * rank
    logger.info('rank {}: seed={}, logdir={}'.format(rank, seed, logger.get_dir()))
    tf.reset_default_graph()
    set_global_seeds(seed)
    env.seed(seed)
    if eval_env is not None:
        eval_env.seed(seed)

    # Disable logging for rank != 0 to avoid noise.
    if rank == 0:
        start_time = time.time()
    training.train(env=env, eval_env=eval_env, param_noise=param_noise,
        action_noise=action_noise, actor=actor, critic=critic, memory=memory, **kwargs)
    env.close()
    if eval_env is not None:
        eval_env.close()
    if rank == 0:
        logger.info('total runtime: {}s'.format(time.time() - start_time)) 
开发者ID:stanfordnmbl,项目名称:osim-rl,代码行数:63,代码来源:train.ddpg.py


注:本文中的baselines.ddpg.models.Critic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。