def __init__(self, venv, desiredShape):
self.vecenv = venv
self.desiredShape = desiredShape
(self.y, self.x, self.c) = desiredShape
self.b = len(self.vecenv.remotes)
# Manually get the dtype
# self.vecenv.remotes[0].send(('get_spaces', None))
# obsSpace, _ = self.vecenv.remotes[0].recv()
# dtype = obsSpace.dtype
# print(dtype)
# print(np.iinfo(dtype).max)
# print(np.iinfo(dtype).min)
# Create the new shapes for actions and observations
observation_space = gym.spaces.Box(low=0,
high=255,
shape=desiredShape,
dtype=np.uint8)
actionSpace = gym.spaces.Discrete(
6) #CHANGED AWAY FROM 6 FOR THE EXPERIEMENTS
VecEnvWrapper.__init__(self,
venv,
observation_space=observation_space,
action_space=actionSpace)
def __init__(self, venv, agent_idx):
""" Got game results.
:param: venv: environment.
:param: agent_idx: the index of victim agent.
"""
VecEnvWrapper.__init__(self, venv)
self.outcomes = []
self.num_games = 0
self.agent_idx = agent_idx
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)
venv.frame_stack_pointer = self
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, logdir, info_keywords=(), **kwargs):
"""
A monitor wrapper for Gym environments, it is used to know the episode reward, length, time and other data.
:param env: (Gym environment) The environment
:param filename: (str) the location to save tensorboard logs
:param info_keywords: (tuple) extra information to log, from the information return of environment.step
"""
VecEnvWrapper.__init__(self, venv=venv, **kwargs)
self.writer = FileWriter(logdir)
self.info_keywords = info_keywords
self.episode_infos = [dict() for _ in range(self.venv.num_envs)]
self.total_steps = 0
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, env, output_directory, record_obs=False, format: str = "gif", unvec=False, reduction=12):
VecEnvWrapper.__init__(self, env)
prefix = "obs_" if record_obs else ""
self.recorders = []
self.reduction = reduction
self.last = reduction
if unvec:
for i in range(self.num_envs):
self.recorders.append(self._create_recorder(output_directory, prefix="{}_{}".format(i, prefix), format=format))
else:
self.recorders.append(self._create_recorder(output_directory, prefix, format))
self.unvec = unvec
self.record_obs = record_obs
self.unvec = unvec
def __init__(self, venv, filename=None, keep_buf=0, info_keywords=()):
VecEnvWrapper.__init__(self, venv)
print('init vecmonitor: ',filename)
self.eprets = None
self.eplens = None
self.epcount = 0
self.tstart = time.time()
if filename:
self.results_writer = ResultsWriter(filename, header={'t_start': self.tstart},
extra_keys=info_keywords)
else:
self.results_writer = None
self.info_keywords = info_keywords
self.keep_buf = keep_buf
if self.keep_buf:
self.epret_buf = deque([], maxlen=keep_buf)
self.eplen_buf = deque([], maxlen=keep_buf)
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):
VecEnvWrapper.__init__(self, venv)
VecMultiEnv.__init__(self, venv.num_envs, venv.num_agents,
venv.observation_space, venv.action_space)
def __init__(self, env, dtype=np.float16):
self.dtype= dtype
self.observation_space = gym.spaces.Box(low=0, high=1.0, shape=env.observation_space.shape, dtype=dtype)
VecEnvWrapper.__init__(self, env, observation_space=self.observation_space)
def __init__(self, venv, r_model):
VecEnvWrapper.__init__(self, venv)
assert callable(r_model)
self.r_model = r_model