Python gym.undo_logger_setup方法代碼示例

# 需要導入模塊: import gym [as 別名]
# 或者: from gym import undo_logger_setup [as 別名]
def setup(exp, single_threaded):
    import gym
    gym.undo_logger_setup()
    from . import policies, tf_util

    config = Config(**exp['config'])
    if 'env_id' in exp:
       env = gym.make(exp['env_id'])
    elif 'env_target' in exp:
       env_target = exp['env_target']
       (module_str, cls_str) = env_target.split(":")
       module = importlib.import_module(module_str)
       cls = getattr(module, cls_str)
       env = cls(**exp['env_params'])
    else:
       raise NotImplementedError
    sess = make_session(single_threaded=single_threaded)
    policy = getattr(policies, exp['policy']['type'])(env.observation_space, env.action_space, **exp['policy']['args'])
    tf_util.initialize()

    return config, env, sess, policy 

# 需要導入模塊: import gym [as 別名]
# 或者: from gym import undo_logger_setup [as 別名]
def test_smoke(env_id):
    """Check that environments start up without errors and that we can extract rewards and observations"""
    gym.undo_logger_setup()
    logging.getLogger().setLevel(logging.INFO)

    env = gym.make(env_id)
    if env.metadata.get('configure.required', False):
        if os.environ.get('FORCE_LATEST_UNIVERSE_DOCKER_RUNTIMES'):  # Used to test universe-envs in CI
            configure_with_latest_docker_runtime_tag(env)
        else:
            env.configure(remotes=1)

    env = wrappers.Unvectorize(env)

    env.reset()
    _rollout(env, timestep_limit=60*30) # Check a rollout 

# 需要導入模塊: import gym [as 別名]
# 或者: from gym import undo_logger_setup [as 別名]
def setup(exp, single_threaded):
    import gym
    gym.undo_logger_setup()
    from . import policies, tf_util

    config = Config(**exp['config'])
    env = gym.make(exp['env_id'])
    sess = make_session(single_threaded=single_threaded)
    policy = getattr(policies, exp['policy']['type'])(env.observation_space, env.action_space, **exp['policy']['args'])
    tf_util.initialize()

    return config, env, sess, policy 

# 需要導入模塊: import gym [as 別名]
# 或者: from gym import undo_logger_setup [as 別名]
def test_nice_vnc_semantics_match(spec, matcher, wrapper):
    # Check that when running over VNC or using the raw environment,
    # semantics match exactly.
    gym.undo_logger_setup()
    logging.getLogger().setLevel(logging.INFO)

    spaces.seed(0)

    vnc_env = spec.make()
    if vnc_env.metadata.get('configure.required', False):
        vnc_env.configure(remotes=1)
    vnc_env = wrapper(vnc_env)
    vnc_env = wrappers.Unvectorize(vnc_env)

    env = gym.make(spec._kwargs['gym_core_id'])

    env.seed(0)
    vnc_env.seed(0)

    # Check that reset observations work
    reset(matcher, env, vnc_env, stage='initial reset')

    # Check a full rollout
    rollout(matcher, env, vnc_env, timestep_limit=50, stage='50 steps')

    # Reset to start a new episode
    reset(matcher, env, vnc_env, stage='reset to new episode')

    # Check that a step into the next episode works
    rollout(matcher, env, vnc_env, timestep_limit=1, stage='1 step in new episode')

    # Make sure env can be reseeded
    env.seed(1)
    vnc_env.seed(1)
    reset(matcher, env, vnc_env, 'reseeded reset')
    rollout(matcher, env, vnc_env, timestep_limit=1, stage='reseeded step') 

# 需要導入模塊: import gym [as 別名]
# 或者: from gym import undo_logger_setup [as 別名]
def env_factory(cmdl, mode):
    # Undo the default logger and configure a new one.
    gym.undo_logger_setup()
    logger = logging.getLogger()
    logger.setLevel(logging.WARNING)

    print(clr("[Main] Constructing %s environment." % mode, attrs=['bold']))
    env = gym.make(cmdl.env_name)

    if hasattr(cmdl, 'rescale_dims'):
        state_dims = (cmdl.rescale_dims, cmdl.rescale_dims)
    else:
        state_dims = env.observation_space.shape[0:2]

    env_class, hist_len, cuda = cmdl.env_class, cmdl.hist_len, cmdl.cuda

    if mode == "training":
        env = PreprocessFrames(env, env_class, hist_len, state_dims, cuda)
        if hasattr(cmdl, 'reward_clamp') and cmdl.reward_clamp:
            env = SqueezeRewards(env)
        if hasattr(cmdl, 'done_after_lost_life') and cmdl.done_after_lost_life:
            env = DoneAfterLostLife(env)
        print('-' * 50)
        return env

    elif mode == "evaluation":
        if cmdl.eval_env_name != cmdl.env_name:
            print(clr("[%s] Warning! evaluating on a different env: %s"
                      % ("Main", cmdl.eval_env_name), 'red', attrs=['bold']))
            env = gym.make(cmdl.eval_env_name)

        env = PreprocessFrames(env, env_class, hist_len, state_dims, cuda)
        env = EvaluationMonitor(env, cmdl)
        print('-' * 50)
        return env