def test_get_wrapper(env_wrapper):
env = gym.make("HalfCheetahBulletEnv-v0")
hyperparams = {"env_wrapper": env_wrapper}
wrapper_class = get_wrapper_class(hyperparams)
if env_wrapper is not None:
env = wrapper_class(env)
check_env(env)
def _preprocess_hyperparams(
self, hyperparams: Dict[str, Any]
) -> Tuple[Dict[str, Any], Optional[Callable], List[BaseCallback]]:
self.n_envs = 4
if self.verbose > 0:
print(f"Using {self.n_envs} environments")
# Convert schedule strings to objects
hyperparams = self._preprocess_schedules(hyperparams)
# Pre-process train_freq
if "train_freq" in hyperparams and isinstance(
hyperparams["train_freq"], list):
hyperparams["train_freq"] = tuple(hyperparams["train_freq"])
# Should we overwrite the number of timesteps?
if self.n_timesteps > 0:
if self.verbose:
print(f"Overwriting n_timesteps with n={self.n_timesteps}")
else:
self.n_timesteps = int(hyperparams["n_timesteps"])
# Pre-process normalize config
hyperparams = self._preprocess_normalization(hyperparams)
# Pre-process policy/buffer keyword arguments
# Convert to python object if needed
for kwargs_key in {
"policy_kwargs",
"replay_buffer_class",
"replay_buffer_kwargs",
}:
if kwargs_key in hyperparams.keys() and isinstance(
hyperparams[kwargs_key], str):
hyperparams[kwargs_key] = eval(hyperparams[kwargs_key])
# Delete keys so the dict can be pass to the model constructor
if "n_envs" in hyperparams.keys():
del hyperparams["n_envs"]
del hyperparams["n_timesteps"]
if "frame_stack" in hyperparams.keys():
self.frame_stack = hyperparams["frame_stack"]
del hyperparams["frame_stack"]
# obtain a class object from a wrapper name string in hyperparams
# and delete the entry
env_wrapper = get_wrapper_class(hyperparams)
if "env_wrapper" in hyperparams.keys():
del hyperparams["env_wrapper"]
callbacks = get_callback_list(hyperparams)
if "callback" in hyperparams.keys():
del hyperparams["callback"]
return hyperparams, env_wrapper, callbacks
def _preprocess_hyperparams(
self, hyperparams: Dict[str, Any]
) -> Tuple[Dict[str, Any], Optional[Callable], List[BaseCallback]]:
self.n_envs = hyperparams.get("n_envs", 1)
if self.verbose > 0:
print(f"Using {self.n_envs} environments")
# Convert model class string to an object if needed (when using HER)
hyperparams = self._preprocess_her_model_class(hyperparams)
hyperparams = self._preprocess_schedules(hyperparams)
# Should we overwrite the number of timesteps?
if self.n_timesteps > 0:
if self.verbose:
print(f"Overwriting n_timesteps with n={self.n_timesteps}")
else:
self.n_timesteps = int(hyperparams["n_timesteps"])
# Pre-process normalize config
hyperparams = self._preprocess_normalization(hyperparams)
# Pre-process policy keyword arguments
if "policy_kwargs" in hyperparams.keys():
# Convert to python object if needed
if isinstance(hyperparams["policy_kwargs"], str):
hyperparams["policy_kwargs"] = eval(
hyperparams["policy_kwargs"])
# Delete keys so the dict can be pass to the model constructor
if "n_envs" in hyperparams.keys():
del hyperparams["n_envs"]
del hyperparams["n_timesteps"]
if "frame_stack" in hyperparams.keys():
self.frame_stack = hyperparams["frame_stack"]
del hyperparams["frame_stack"]
# obtain a class object from a wrapper name string in hyperparams
# and delete the entry
env_wrapper = get_wrapper_class(hyperparams)
if "env_wrapper" in hyperparams.keys():
del hyperparams["env_wrapper"]
callbacks = get_callback_list(hyperparams)
if "callback" in hyperparams.keys():
del hyperparams["callback"]
return hyperparams, env_wrapper, callbacks
