def __init__(self,
venv,
directory,
record_video_trigger,
video_length=200):
"""
# Arguments
venv: VecEnv to wrap
directory: Where to save videos
record_video_trigger:
Function that defines when to start recording.
The function takes the current number of step,
and returns whether we should start recording or not.
video_length: Length of recorded video
"""
VecEnvWrapper.__init__(self, venv)
self.record_video_trigger = record_video_trigger
self.video_recorder = None
self.directory = os.path.abspath(directory)
if not os.path.exists(self.directory):
os.mkdir(self.directory)
self.file_prefix = "vecenv"
self.file_infix = "{}".format(os.getpid())
self.step_id = 0
self.video_length = video_length
self.recording = False
self.recorded_frames = 0
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 __init__(self, venv, nstack):
self.venv = venv
self.nstack = nstack
wos = venv.observation_space # wrapped ob space
self.shape_dim0 = wos.shape[0]
low = np.repeat(wos.low, self.nstack, axis=0)
high = np.repeat(wos.high, self.nstack, axis=0)
self.stacked_obs = torch.zeros((venv.num_envs,) + low.shape)
observation_space = gym.spaces.Box(
low=low, high=high, dtype=venv.observation_space.dtype
)
VecEnvWrapper.__init__(self, venv, observation_space=observation_space)
def __init__(self,
venv,
ob=True,
ret=True,
clipob=10.,
cliprew=10.,
gamma=0.99,
epsilon=1e-8):
VecEnvWrapper.__init__(self, venv)
self.ob_rms = RunningMeanStd(
shape=self.observation_space.shape) if ob else None
self.ret_rms = RunningMeanStd(shape=()) if ret else None
self.clipob = clipob
self.cliprew = cliprew
self.ret = np.zeros(self.num_envs)
self.gamma = gamma
self.epsilon = epsilon
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 __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 close(self):
VecEnvWrapper.close(self)
self.close_video_recorder()