mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-05-24 22:25:13 +00:00
* Added working her version, Online sampling is missing. * Updated test_her. * Added first version of online her sampling. Still problems with tensor dimensions. * Reformat * Fixed tests * Added some comments. * Updated changelog. * Add missing init file * Fixed some small bugs. * Reduced arguments for HER, small changes. * Added getattr. Fixed bug for online sampling. * Updated save/load funtions. Small changes. * Added her to init. * Updated save method. * Updated her ratio. * Move obs_wrapper * Added DQN test. * Fix potential bug * Offline and online her share same sample_goal function. * Changed lists into arrays. * Updated her test. * Fix online sampling * Fixed action bug. Updated time limit for episodes. * Updated convert_dict method to take keys as arguments. * Renamed obs dict wrapper. * Seed bit flipping env * Remove get_episode_dict * Add fast online sampling version * Added documentation. * Vectorized reward computation * Vectorized goal sampling * Update time limit for episodes in online her sampling. * Fix max episode length inference * Bug fix for Fetch envs * Fix for HER + gSDE * Reformat (new black version) * Added info dict to compute new reward. Check her_replay_buffer again. * Fix info buffer * Updated done flag. * Fixes for gSDE * Offline her version uses now HerReplayBuffer as episode storage. * Fix num_timesteps computation * Fix get torch params * Vectorized version for offline sampling. * Modified offline her sampling to use sample method of her_replay_buffer * Updated HER tests. * Updated documentation * Cleanup docstrings * Updated to review comments * Fix pytype * Update according to review comments. * Removed random goal strategy. Updated sample transitions. * Updated migration. Removed time signal removal. * Update doc * Fix potential load issue * Add VecNormalize support for dict obs * Updated saving/loading replay buffer for HER. * Fix test memory usage * Fixed save/load replay buffer. * Fixed save/load replay buffer * Fixed transition index after loading replay buffer in online sampling * Better error handling * Add tests for get_time_limit * More tests for VecNormalize with dict obs * Update doc * Improve HER description * Add test for sde support * Add comments * Add comments * Remove check that was always valid * Fix for terminal observation * Updated buffer size in offline version and reset of HER buffer * Reformat * Update doc * Remove np.empty + add doc * Fix loading * Updated loading replay buffer * Separate online and offline sampling + bug fixes * Update tensorboard log name * Version bump * Bug fix for special case Co-authored-by: Antonin Raffin <antonin.raffin@dlr.de> Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
69 lines
2.3 KiB
Python
69 lines
2.3 KiB
Python
# flake8: noqa F401
|
|
import typing
|
|
from copy import deepcopy
|
|
from typing import Optional, Type, Union
|
|
|
|
from stable_baselines3.common.vec_env.base_vec_env import CloudpickleWrapper, VecEnv, VecEnvWrapper
|
|
from stable_baselines3.common.vec_env.dummy_vec_env import DummyVecEnv
|
|
from stable_baselines3.common.vec_env.subproc_vec_env import SubprocVecEnv
|
|
from stable_baselines3.common.vec_env.vec_check_nan import VecCheckNan
|
|
from stable_baselines3.common.vec_env.vec_frame_stack import VecFrameStack
|
|
from stable_baselines3.common.vec_env.vec_normalize import VecNormalize
|
|
from stable_baselines3.common.vec_env.vec_transpose import VecTransposeImage
|
|
from stable_baselines3.common.vec_env.vec_video_recorder import VecVideoRecorder
|
|
|
|
# Avoid circular import
|
|
if typing.TYPE_CHECKING:
|
|
from stable_baselines3.common.type_aliases import GymEnv
|
|
|
|
|
|
def unwrap_vec_wrapper(env: Union["GymEnv", VecEnv], vec_wrapper_class: Type[VecEnvWrapper]) -> Optional[VecEnvWrapper]:
|
|
"""
|
|
Retrieve a ``VecEnvWrapper`` object by recursively searching.
|
|
|
|
:param env:
|
|
:param vec_wrapper_class:
|
|
:return:
|
|
"""
|
|
env_tmp = env
|
|
while isinstance(env_tmp, VecEnvWrapper):
|
|
if isinstance(env_tmp, vec_wrapper_class):
|
|
return env_tmp
|
|
env_tmp = env_tmp.venv
|
|
return None
|
|
|
|
|
|
def unwrap_vec_normalize(env: Union["GymEnv", VecEnv]) -> Optional[VecNormalize]:
|
|
"""
|
|
:param env:
|
|
:return:
|
|
"""
|
|
return unwrap_vec_wrapper(env, VecNormalize) # pytype:disable=bad-return-type
|
|
|
|
|
|
def is_wrapped(env: Union["GymEnv", VecEnv], vec_wrapper_class: Type[VecEnvWrapper]) -> bool:
|
|
"""
|
|
Check if an environment is already wrapped by a given ``VecEnvWrapper``.
|
|
|
|
:param env:
|
|
:param vec_wrapper_class:
|
|
:return:
|
|
"""
|
|
return unwrap_vec_wrapper(env, vec_wrapper_class) is not None
|
|
|
|
|
|
# Define here to avoid circular import
|
|
def sync_envs_normalization(env: "GymEnv", eval_env: "GymEnv") -> None:
|
|
"""
|
|
Sync eval env and train env when using VecNormalize
|
|
|
|
:param env:
|
|
:param eval_env:
|
|
"""
|
|
env_tmp, eval_env_tmp = env, eval_env
|
|
while isinstance(env_tmp, VecEnvWrapper):
|
|
if isinstance(env_tmp, VecNormalize):
|
|
eval_env_tmp.obs_rms = deepcopy(env_tmp.obs_rms)
|
|
eval_env_tmp.ret_rms = deepcopy(env_tmp.ret_rms)
|
|
env_tmp = env_tmp.venv
|
|
eval_env_tmp = eval_env_tmp.venv
|