How to use the lagom.envs.wrappers.ClipAction function in lagom

To help you get started, we’ve selected a few lagom examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

zuoxingdong / lagom / examples / reinforcement_learning / vpg / logs / default / source_files / experiment.py View on Github

def _make_env():
        env = gym.make(config['env.id'])
        env = env.env  # strip out gym TimeLimit, TODO: remove until gym update it
        env = TimeLimit(env, env.spec.max_episode_steps)
        if config['env.clip_action'] and isinstance(env.action_space, Box):
            env = ClipAction(env)
        return env
    env = make_vec_env(_make_env, 1, seed)  # single environment

zuoxingdong / lagom / baselines / openaies / logs / default / source_files / experiment.py View on Github

def _make_env():
        env = gym.make(config['env.id'])
        env = env.env  # strip out gym TimeLimit, TODO: remove until gym update it
        env = TimeLimit(env, env.spec.max_episode_steps)
        if config['env.clip_action'] and isinstance(env.action_space, Box):
            env = ClipAction(env)
        return env
    env = make_vec_env(_make_env, 1, seed)  # single environment

zuoxingdong / lagom / examples / reinforcement_learning / ppo / experiment.py View on Github

def _make_env():
        env = gym.make(config['env.id'])
        env = env.env  # strip out gym TimeLimit, TODO: remove until gym update it
        env = TimeLimit(env, env.spec.max_episode_steps)
        if config['env.clip_action'] and isinstance(env.action_space, Box):
            env = ClipAction(env)
        return env
    env = make_vec_env(_make_env, 1, seed)  # single environment

zuoxingdong / lagom / baselines / ddpg / logs / default / source_files / experiment.py View on Github

def _make_env():
        env = gym.make(config['env.id'])
        env = env.env  # strip out gym TimeLimit, TODO: remove until gym update it
        env = TimeLimit(env, env.spec.max_episode_steps)
        env = ClipAction(env)
        return env
    env = make_vec_env(_make_env, 1, seed)  # single environment

zuoxingdong / lagom / examples / reinforcement_learning / vpg / experiment.py View on Github

def _make_env():
        env = gym.make(config['env.id'])
        env = env.env  # strip out gym TimeLimit, TODO: remove until gym update it
        env = TimeLimit(env, env.spec.max_episode_steps)
        if config['env.time_aware_obs']:
            env = TimeAwareObservation(env)
        if config['env.clip_action'] and isinstance(env.action_space, Box):
            env = ClipAction(env)
        return env
    env = make_vec_env(_make_env, 1, seed, 'serial')  # single environment

zuoxingdong / lagom / baselines / td3 / logs / default / source_files / experiment.py View on Github

def _make_env():
        env = gym.make(config['env.id'])
        env = env.env  # strip out gym TimeLimit, TODO: remove until gym update it
        env = TimeLimit(env, env.spec.max_episode_steps)
        env = ClipAction(env)
        return env
    env = make_vec_env(_make_env, 1, seed)  # single environment

zuoxingdong / lagom / examples / reinforcement_learning / td3 / experiment.py View on Github

def _make_env():
        env = gym.make(config['env.id'])
        env = env.env  # strip out gym TimeLimit, TODO: remove until gym update it
        env = TimeLimit(env, env.spec.max_episode_steps)
        env = ClipAction(env)
        return env
    env = make_vec_env(_make_env, 1, seed)  # single environment

How to use the lagom.envs.wrappers.ClipAction function in lagom

To help you get started, we’ve selected a few lagom examples, based on popular ways it is used in public projects.

lagom

Package Health Score

Popular lagom functions

Similar packages