mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-06-27 03:11:57 +00:00
c5adad82b2
* IM compat. modif from old fork * mp her working, without offline sampling * update readme and doc * fix discrete action/obs space case * handle offline sampling * fix pos to be consistent with the old version * improve typing and docstring * fix discrete obs special case * new her, using episode uid * deal with full buffer * offline not implemented * info storage; compute_reward as arg; offline sampling error * offline sampling; timeout_termination; fix last_trans detection * rm max_episode_length from tests * fix loading and loading test * Fix episode sampling strategy * Episode interrupted not valid * Typo * Fix infos sampling, next_obs desired goals, offline sampling * update tests for multienvs * speed up code * handle timeout sampling when samping * give up ep_uid for ep_start and ep_lenght * speed up sampling * Improve docstring * Typos and renaming * Fix typing * Fix linter warnings * Renaming + add note * fix reward type * Fix future sampling strategy * Fix future goal selection strategy * env_fn as lambda * Re-fix linter warnings * Formatting * Fix offline sampling * restore the initial performance budget * Remove max_episode_length for HerReplayBuffer kwargs * SubprcVecEnv compat test * Dedicated SubrocVecEnv test rm n_envs from parametrization * Back to using the env arg instead of compute_reward * Up VecEnv import * fix lint warnings * fix docstring * Fix device issue * actor_loss_modifier in SAV and TD3 * Merge RewardModifier and ActorLossModifier into Surgeon * update surgeon for rnd * fix uninteded merge * fix uninteded merge * fix unintended merge * Rm unintended merge * Fix KeyError * Remove useless `all_inds` * Minor docstring format * Fix hint * speedup! * Speedup again * speedup * np.nonzero * fix env normalization * flat sampling for speedup * typo * drop online * format * remove observation from env_cheker (see #1335) * update changelog * default device to "auto" * add comment for info storage * add comment for ep_start and ep_length attributes * a[b][c] to a[b, c] * comment flatnonzero and unravel_index * update _sample_goals docstring * Fix future gaol sampling for split episode * add informative error message for learning_starts too small * use keyword arg for env * try fix pytye * Update stable_baselines3/common/off_policy_algorithm.py Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org> * Add `copy_info_dict` option * Ignore pytype * Update changelog * Rename variables and improve documentation * Ignore new bug bear rule * Add note about future strategy * Add deprecation warning * Fix bug trying to pickle buffer kwargs --------- Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
94 lines
3.1 KiB
TOML
94 lines
3.1 KiB
TOML
[tool.ruff]
|
|
# Same as Black.
|
|
line-length = 127
|
|
# Assume Python 3.7
|
|
target-version = "py37"
|
|
# See https://beta.ruff.rs/docs/rules/
|
|
select = ["E", "F", "B", "UP", "C90", "RUF"]
|
|
# Ignore explicit stacklevel`
|
|
ignore = ["B028"]
|
|
|
|
[tool.ruff.per-file-ignores]
|
|
# Default implementation in abstract methods
|
|
"./stable_baselines3/common/callbacks.py"= ["B027"]
|
|
"./stable_baselines3/common/noise.py"= ["B027"]
|
|
|
|
|
|
[tool.ruff.mccabe]
|
|
# Unlike Flake8, default to a complexity level of 10.
|
|
max-complexity = 15
|
|
|
|
[tool.black]
|
|
line-length = 127
|
|
|
|
[tool.isort]
|
|
profile = "black"
|
|
line_length = 127
|
|
src_paths = ["stable_baselines3"]
|
|
|
|
[tool.pytype]
|
|
inputs = ["stable_baselines3"]
|
|
disable = ["pyi-error"]
|
|
|
|
[tool.mypy]
|
|
ignore_missing_imports = true
|
|
follow_imports = "silent"
|
|
show_error_codes = true
|
|
exclude = """(?x)(
|
|
stable_baselines3/a2c/a2c.py$
|
|
| stable_baselines3/common/base_class.py$
|
|
| stable_baselines3/common/buffers.py$
|
|
| stable_baselines3/common/callbacks.py$
|
|
| stable_baselines3/common/distributions.py$
|
|
| stable_baselines3/common/envs/bit_flipping_env.py$
|
|
| stable_baselines3/common/envs/identity_env.py$
|
|
| stable_baselines3/common/envs/multi_input_envs.py$
|
|
| stable_baselines3/common/logger.py$
|
|
| stable_baselines3/common/off_policy_algorithm.py$
|
|
| stable_baselines3/common/on_policy_algorithm.py$
|
|
| stable_baselines3/common/policies.py$
|
|
| stable_baselines3/common/save_util.py$
|
|
| stable_baselines3/common/sb2_compat/rmsprop_tf_like.py$
|
|
| stable_baselines3/common/utils.py$
|
|
| stable_baselines3/common/vec_env/__init__.py$
|
|
| stable_baselines3/common/vec_env/base_vec_env.py$
|
|
| stable_baselines3/common/vec_env/dummy_vec_env.py$
|
|
| stable_baselines3/common/vec_env/subproc_vec_env.py$
|
|
| stable_baselines3/common/vec_env/util.py$
|
|
| stable_baselines3/common/vec_env/vec_extract_dict_obs.py$
|
|
| stable_baselines3/common/vec_env/vec_frame_stack.py$
|
|
| stable_baselines3/common/vec_env/vec_monitor.py$
|
|
| stable_baselines3/common/vec_env/vec_normalize.py$
|
|
| stable_baselines3/common/vec_env/vec_transpose.py$
|
|
| stable_baselines3/common/vec_env/vec_video_recorder.py$
|
|
| stable_baselines3/dqn/dqn.py$
|
|
| stable_baselines3/dqn/policies.py$
|
|
| stable_baselines3/her/her_replay_buffer.py$
|
|
| stable_baselines3/ppo/ppo.py$
|
|
| stable_baselines3/sac/policies.py$
|
|
| stable_baselines3/sac/sac.py$
|
|
| stable_baselines3/td3/policies.py$
|
|
| stable_baselines3/td3/td3.py$
|
|
| tests/test_logger.py$
|
|
| tests/test_train_eval_mode.py$
|
|
)"""
|
|
|
|
[tool.pytest.ini_options]
|
|
# Deterministic ordering for tests; useful for pytest-xdist.
|
|
env = [
|
|
"PYTHONHASHSEED=0"
|
|
]
|
|
|
|
filterwarnings = [
|
|
# Tensorboard warnings
|
|
"ignore::DeprecationWarning:tensorboard",
|
|
# Gym warnings
|
|
"ignore:Parameters to load are deprecated.:DeprecationWarning",
|
|
"ignore:the imp module is deprecated in favour of importlib:PendingDeprecationWarning",
|
|
"ignore::UserWarning:gym",
|
|
"ignore:SelectableGroups dict interface is deprecated.:DeprecationWarning",
|
|
"ignore:`np.bool` is a deprecated alias for the builtin `bool`:DeprecationWarning",
|
|
]
|
|
markers = [
|
|
"expensive: marks tests as expensive (deselect with '-m \"not expensive\"')"
|
|
]
|