def __init__(self, venv, training=True, norm_obs=True, norm_reward=True,
clip_obs=10., clip_reward=10., gamma=0.99, epsilon=1e-8, context_bounds=None):
VecEnvWrapper.__init__(self, venv)
self.context_bounds = context_bounds
self.dim_off = None
if self.context_bounds is not None:
assert len(self.observation_space.shape) == 1
self.dim_off = self.observation_space.shape[0] - self.context_bounds[0].shape[0]
# If the offset dimension is not None, i.e. if we normalize the context observations differently, initialize
# the RunningMeanStd with a different dimensionality - it is assumed that the context follows the original state
if self.dim_off is None:
self.obs_rms = RunningMeanStd(shape=self.observation_space.shape)
else:
if len(self.observation_space.shape) != 1:
raise RuntimeError("Only simple continuous observation spaces support an offset index")
self.obs_rms = RunningMeanStd(shape=(self.dim_off,))
self.ret_rms = RunningMeanStd(shape=())
self.clip_obs = clip_obs
self.clip_reward = clip_reward
# Returns: discounted rewards
self.ret = np.zeros(self.num_envs)
self.gamma = gamma
self.epsilon = epsilon
self.training = training
self.norm_obs = norm_obs
self.norm_reward = norm_reward
self.old_obs = None
self.old_rews = None
def __init__(self, venv, n_stack):
self.venv = venv
self.n_stack = n_stack
wrapped_obs_space = venv.observation_space
low = np.repeat(wrapped_obs_space.low, self.n_stack, axis=-1)
high = np.repeat(wrapped_obs_space.high, self.n_stack, axis=-1)
self.stackedobs = np.zeros((venv.num_envs, ) + low.shape, low.dtype)
observation_space = spaces.Box(low=low,
high=high,
dtype=venv.observation_space.dtype)
VecEnvWrapper.__init__(self, venv, observation_space=observation_space)
def __init__(self,
venv,
raise_exception=False,
warn_once=True,
check_inf=True):
VecEnvWrapper.__init__(self, venv)
self.raise_exception = raise_exception
self.warn_once = warn_once
self.check_inf = check_inf
self._actions = None
self._observations = None
self._user_warned = False
def set_venv(self, venv):
"""
Sets the vector environment to wrap to venv.
Also sets attributes derived from this such as `num_env`.
:param venv: (VecEnv)
"""
if self.venv is not None:
raise ValueError("Trying to set venv of already initialized VecNormalize wrapper.")
VecEnvWrapper.__init__(self, venv)
if self.obs_rms.mean.shape != self.observation_space.shape:
raise ValueError("venv is incompatible with current statistics.")
self.ret = np.zeros(self.num_envs)
def __init__(self, venv, training=True, norm_obs=True, norm_reward=True,
clip_obs=10., clip_reward=10., gamma=0.99, epsilon=1e-8):
VecEnvWrapper.__init__(self, venv)
self.obs_rms = RunningMeanStd(shape=self.observation_space.shape)
self.ret_rms = RunningMeanStd(shape=())
self.clip_obs = clip_obs
self.clip_reward = clip_reward
# Returns: discounted rewards
self.ret = np.zeros(self.num_envs)
self.gamma = gamma
self.epsilon = epsilon
self.training = training
self.norm_obs = norm_obs
self.norm_reward = norm_reward
self.old_obs = np.array([])
def __init__(self,
venv,
video_folder,
record_video_trigger,
video_length=200,
name_prefix='rl-video'):
VecEnvWrapper.__init__(self, venv)
self.env = venv
# Temp variable to retrieve metadata
temp_env = venv
# Unwrap to retrieve metadata dict
# that will be used by gym recorder
while isinstance(temp_env, VecNormalize) or isinstance(
temp_env, VecFrameStack):
temp_env = temp_env.venv
if isinstance(temp_env, DummyVecEnv) or isinstance(
temp_env, SubprocVecEnv):
metadata = temp_env.get_attr('metadata')[0]
else:
metadata = temp_env.metadata
self.env.metadata = metadata
self.record_video_trigger = record_video_trigger
self.video_recorder = None
self.video_folder = os.path.abspath(video_folder)
# Create output folder if needed
os.makedirs(self.video_folder, exist_ok=True)
self.name_prefix = name_prefix
self.step_id = 0
self.video_length = video_length
self.recording = False
self.recorded_frames = 0
def close(self):
VecEnvWrapper.close(self)
self.close_video_recorder()
def __init__(self, venv,):
VecEnvWrapper.__init__(self, venv)