stable-baselines3/stable_baselines3/common/vec_env/__init__.py

75 lines
2.7 KiB
Python
Raw Normal View History

2019-09-20 13:18:25 +00:00
# flake8: noqa F401
2020-03-12 11:34:25 +00:00
import typing
2019-11-14 13:35:00 +00:00
from copy import deepcopy
from typing import Optional, Type, Union
from stable_baselines3.common.vec_env.base_vec_env import CloudpickleWrapper, VecEnv, VecEnvWrapper
2020-05-05 13:02:35 +00:00
from stable_baselines3.common.vec_env.dummy_vec_env import DummyVecEnv
Dictionary Observations (#243) * First commit * Fixing missing refs from a quick merge from master * Reformat * Adding DictBuffers * Reformat * Minor reformat * added slow dict test. Added SACMultiInputPolicy for future. Added private static image transpose helper to common policy * Ran black on buffers * Ran isort * Adding StackedObservations classes used within VecStackEnvs wrappers. Made test_dict_env shorter and removed slow * Running isort :facepalm * Fixed typing issues * Adding docstrings and typing. Using util for moving data to device. * Fixed trailing commas * Fix types * Minor edits * Avoid duplicating code * Fix calls to parents * Adding assert to buffers. Updating changelong * Running format on buffers * Adding multi-input policies to dqn,td3,a2c. Fixing warnings. Fixed bug with DictReplayBuffer as Replay buffers use only 1 env * Fixing warnings, splitting is_vectorized_observation into multiple functions based on space type * Created envs folder in common. Updated imports. Moved stacked_obs to vec_env folder * Moved envs to envs directory. Moved stacked obs to vec_envs. Started update on documentation * Fixes * Running code style * Update docstrings on torch_layers * Decapitalize non-constant variables * Using NatureCNN architecture in combined extractor. Increasing img size in multi input env. Adding memory reduction in test * Update doc * Update doc * Fix format * Removing NineRoom env. Using nested preprocess. Removing mutable default args * running code style * Passing channel check through to stacked dict observations. * Running black * Adding channel control to SimpleMultiObsEnv. Passing check_channels to CombinedExtractor * Remove optimize memory for dict buffers * Update doc * Move identity env * Minor edits + bump version * Update doc * Fix doc build * Bug fixes + add support for more type of dict env * Fixes + add multi env test * Add support for vectranspose * Fix stacked obs for dict and add tests * Add check for nested spaces. Fix dict-subprocvecenv test * Fix (single) pytype error * Simplify CombinedExtractor * Fix tests * Fix check * Merge branch 'master' into feat/dict_observations * Fix for net_arch with dict and vector obs * Fixes * Add consistency test * Update env checker * Add some docs on dict obs * Update default CNN feature vector size * Refactor HER (#351) * Start refactoring HER * Fixes * Additional fixes * Faster tests * WIP: HER as a custom replay buffer * New replay only version (working with DQN) * Add support for all off-policy algorithms * Fix saving/loading * Remove ObsDictWrapper and add VecNormalize tests with dict * Stable-Baselines3 v1.0 (#354) * Bump version and update doc * Fix name * Apply suggestions from code review Co-authored-by: Adam Gleave <adam@gleave.me> * Update docs/index.rst Co-authored-by: Adam Gleave <adam@gleave.me> * Update wording for RL zoo Co-authored-by: Adam Gleave <adam@gleave.me> * Add gym-pybullet-drones project (#358) * Update projects.rst Added gym-pybullet-drones * Update projects.rst Longer title underline * Update changelog Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org> * Include SuperSuit in projects (#359) * include supersuit * longer title underline * Update changelog.rst * Fix default arguments + add bugbear (#363) * Fix potential bug + add bug bear * Remove unused variables * Minor: version bump * Add code of conduct + update doc (#373) * Add code of conduct * Fix DQN doc example * Update doc (channel-last/first) * Apply suggestions from code review Co-authored-by: Anssi <kaneran21@hotmail.com> * Apply suggestions from code review Co-authored-by: Adam Gleave <adam@gleave.me> Co-authored-by: Anssi <kaneran21@hotmail.com> Co-authored-by: Adam Gleave <adam@gleave.me> * Make installation command compatible with ZSH (#376) * Add quotes * Add Zsh bracket info * Add clarify pip installation line * Make note bold * Add Zsh pip installation note * Add handle timeouts param * Fixes * Fixes (buffer size, extend test) * Fix `max_episode_length` redefinition * Fix potential issue * Add some docs on dict obs * Fix performance bug * Fix slowdown * Add package to install (#378) * Add package to install * Update docs packages installation command Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * Fix backward compat + add test * Fix VecEnv detection * Update doc * Fix vec env check * Support for `VecMonitor` for gym3-style environments (#311) * add vectorized monitor * auto format of the code * add documentation and VecExtractDictObs * refactor and add test cases * add test cases and format * avoid circular import and fix doc * fix type * fix type * oops * Update stable_baselines3/common/monitor.py Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * Update stable_baselines3/common/monitor.py Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * add test cases * update changelog * fix mutable argument * quick fix * Apply suggestions from code review * fix terminal observation for gym3 envs * delete comment * Update doc and bump version * Add warning when already using `Monitor` wrapper * Update vecmonitor tests * Fixes Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * Reformat * Fixed loading of ``ent_coef`` for ``SAC`` and ``TQC``, it was not optimized anymore (#392) * Fix ent coef loading bug * Add test * Add comment * Reuse save path * Add test for GAE + rename `RolloutBuffer.dones` for clarification (#375) * Fix return computation + add test for GAE * Rename `last_dones` to `episode_starts` for clarification * Revert advantage * Cleanup test * Rename variable * Clarify return computation * Clarify docs * Add multi-episode rollout test * Reformat Co-authored-by: Anssi "Miffyli" Kanervisto <kaneran21@hotmail.com> * Fixed saving of `A2C` and `PPO` policy when using gSDE (#401) * Improve doc and replay buffer loading * Add support for images * Fix doc * Update Procgen doc * Update changelog * Update docstrings Co-authored-by: Adam Gleave <adam@gleave.me> Co-authored-by: Jacopo Panerati <jacopo.panerati@utoronto.ca> Co-authored-by: Justin Terry <justinkterry@gmail.com> Co-authored-by: Anssi <kaneran21@hotmail.com> Co-authored-by: Tom Dörr <tomdoerr96@gmail.com> Co-authored-by: Tom Dörr <tom.doerr@tum.de> Co-authored-by: Costa Huang <costa.huang@outlook.com> * Update doc and minor fixes * Update doc * Added note about MultiInputPolicy in error of NatureCNN * Merge branch 'master' into feat/dict_observations * Address comments * Naming clarifications * Actually saving the file would be nice * Fix edge case when doing online sampling with HER * Cleanup * Add sanity check Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> Co-authored-by: Anssi "Miffyli" Kanervisto <kaneran21@hotmail.com> Co-authored-by: Adam Gleave <adam@gleave.me> Co-authored-by: Jacopo Panerati <jacopo.panerati@utoronto.ca> Co-authored-by: Justin Terry <justinkterry@gmail.com> Co-authored-by: Tom Dörr <tomdoerr96@gmail.com> Co-authored-by: Tom Dörr <tom.doerr@tum.de> Co-authored-by: Costa Huang <costa.huang@outlook.com>
2021-05-11 10:29:30 +00:00
from stable_baselines3.common.vec_env.stacked_observations import StackedDictObservations, StackedObservations
2020-05-05 13:02:35 +00:00
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_extract_dict_obs import VecExtractDictObs
2020-05-05 13:02:35 +00:00
from stable_baselines3.common.vec_env.vec_frame_stack import VecFrameStack
from stable_baselines3.common.vec_env.vec_monitor import VecMonitor
2020-05-05 13:02:35 +00:00
from stable_baselines3.common.vec_env.vec_normalize import VecNormalize
from stable_baselines3.common.vec_env.vec_transpose import VecTransposeImage
2020-05-05 14:28:38 +00:00
from stable_baselines3.common.vec_env.vec_video_recorder import VecVideoRecorder
2019-11-14 13:35:00 +00:00
2020-03-12 11:34:25 +00:00
# Avoid circular import
if typing.TYPE_CHECKING:
2020-05-05 13:02:35 +00:00
from stable_baselines3.common.type_aliases import GymEnv
2019-11-14 13:35:00 +00:00
2020-03-12 11:34:25 +00:00
def unwrap_vec_wrapper(env: Union["GymEnv", VecEnv], vec_wrapper_class: Type[VecEnvWrapper]) -> Optional[VecEnvWrapper]:
2019-11-14 13:35:00 +00:00
"""
Retrieve a ``VecEnvWrapper`` object by recursively searching.
:param env:
:param vec_wrapper_class:
:return:
2019-11-14 13:35:00 +00:00
"""
env_tmp = env
while isinstance(env_tmp, VecEnvWrapper):
if isinstance(env_tmp, vec_wrapper_class):
2019-11-14 13:35:00 +00:00
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_vecenv_wrapped(env: Union["GymEnv", VecEnv], vec_wrapper_class: Type[VecEnvWrapper]) -> bool:
Implement HER (#120) * 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>
2020-10-22 09:56:43 +00:00
"""
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
2019-11-14 13:35:00 +00:00
# Define here to avoid circular import
def sync_envs_normalization(env: "GymEnv", eval_env: "GymEnv") -> None:
2019-11-14 13:35:00 +00:00
"""
Sync eval env and train env when using VecNormalize
:param env:
:param eval_env:
2019-11-14 13:35:00 +00:00
"""
env_tmp, eval_env_tmp = env, eval_env
while isinstance(env_tmp, VecEnvWrapper):
if isinstance(env_tmp, VecNormalize):
# Only synchronize if observation normalization exists
if hasattr(env_tmp, "obs_rms"):
eval_env_tmp.obs_rms = deepcopy(env_tmp.obs_rms)
2020-03-12 11:34:25 +00:00
eval_env_tmp.ret_rms = deepcopy(env_tmp.ret_rms)
2019-11-14 13:35:00 +00:00
env_tmp = env_tmp.venv
2020-01-20 10:17:55 +00:00
eval_env_tmp = eval_env_tmp.venv