Commit Graph

Select branches

Hide Pull Requests

master

Mono Color

• adfbeb1b01 Fix typo in changelog (#237) master Antonin RAFFIN 2024-04-01 16:07:19 +0200
• 17cd797d5c Release v2.3.0 (#236) Antonin RAFFIN 2024-03-31 20:39:46 +0200
• 34eceaf382 Log success rate for PPO variants (#235) Antonin RAFFIN 2024-03-31 19:51:48 +0200
• 89d0113037 Update ruff and SB3 dependencies (#232) Antonin RAFFIN 2024-03-11 14:29:47 +0100
• 7dd6c39fba Fix MaskablePPO type annotations (#233) Antonin RAFFIN 2024-03-11 14:10:12 +0100
• cd31e89e26 Fix `train_freq` type annotation for TQC and QR-DQN (#229) Armand du Parc Locmaria 2024-01-24 10:44:38 +0100
• bc3c0a9595 Add notes about MaskablePPO (#227) Tjeerd Bakker 2024-01-18 17:03:02 +0100
• 3f0c5088b3 Update QRDQN defaults (#225) Antonin RAFFIN 2024-01-12 16:17:44 +0100
• 1553b66ee4 Update `_process_sequence()` docstring (#219) Rogério Júnior 2023-12-05 04:59:48 -0800
• 94a5daab02 Update SB3 version (#217) Antonin RAFFIN 2023-11-18 00:02:47 +0100
• ebb74c44ec Release v2.2.0 (#216) Antonin RAFFIN 2023-11-16 18:06:50 +0100
• 6cfa588c0f Update pytorch version Antonin Raffin 2023-11-16 18:00:31 +0100
• c965ba9d3b Remove PyType and upgrade to latest SB3 version (#215) Antonin RAFFIN 2023-11-08 09:50:06 +0100
• 5e437fc4dc Add rollout_buffer_class to TRPO (#214) M. Ernestus 2023-10-30 16:10:41 +0100
• 4d7ed004af Sync SB3 Contrib with SB3 (#213) Antonin RAFFIN 2023-10-25 14:32:51 +0200
• 5be11deaf3 Fix RTD default theme Antonin Raffin 2023-09-07 09:53:40 +0200
• cf4ed5fe65 Release v2.1.0 (#204) Antonin RAFFIN 2023-08-17 22:17:12 +0200
• 4e99b74e90
  Merge branch 'Stable-Baselines-Team:master' into master Paul Auerbach 2023-08-07 14:34:38 +0200
• bc08ee985e Added save_load test for SACD Paul Auerbach 2023-08-07 14:23:07 +0200
• d97dbc727c Added doc page for SACD Paul Auerbach 2023-08-07 14:03:12 +0200
• 610fd3dcf6 Added run test for SACD Paul Auerbach 2023-08-07 13:16:00 +0200
• fca2c6d490 Prepared files for merge request (minor cleanup) Paul Auerbach 2023-08-04 18:19:34 +0200
• 4a37f58259 Code style changes Paul Auerbach 2023-08-02 13:52:40 +0200
• 7711813dbb Reworked code to work whith more than 2 critic networks Paul Auerbach 2023-08-02 13:17:22 +0200
• 875b8bca0d Fixed bugs in that lead to wrong results, currently only working with 2 critics Paul Auerbach 2023-08-01 15:09:55 +0200
• dfa23bdf9c
  Bugfix/ppo mask stats window size (#199) PatrickHelm 2023-08-01 11:53:27 +0200
• a14ae69b6b Added first version of SAC Discrete, which is running but not learning currently Paul Auerbach 2023-07-31 16:07:08 +0200
• 35f06254ba
  Drop python 3.7, add 3.11 and update github templates (#194) Antonin RAFFIN 2023-07-03 12:45:20 +0200
• de92025bb2
  Prepare Release v2.0 (#192) Antonin RAFFIN 2023-06-23 13:10:17 +0200
• 6e1aba45e3
  Update version and fix #188 (#190) Antonin RAFFIN 2023-06-07 16:51:42 +0200
• c84079d4f3 Update pypi build command Antonin Raffin 2023-05-24 11:41:28 +0200
• d467d7a844
  Update AsyncEval seeding (#185) Antonin RAFFIN 2023-05-20 10:57:31 +0200
• 86fb056fda
  Update doc: switch from Gym to Gymnasium (#182) Antonin RAFFIN 2023-05-10 11:40:40 +0200
• 21cc96cafd
  Add Gymnasium support (#152) Antonin RAFFIN 2023-04-14 13:52:07 +0200
• a84ad3aa7d
  Release v1.8.0 (#173) Antonin RAFFIN 2023-04-08 15:50:04 +0200
• aacded79c5
  Add stats window argument (#171) Jonas Reiher 2023-04-05 18:47:27 +0200
• ce115982aa
  Fix QR-DQN type hints (#170) Antonin RAFFIN 2023-03-30 11:50:26 +0200
• b5fd6e65ba
  Update SB3 and config (#167) Antonin RAFFIN 2023-03-20 12:35:37 +0100
• 1f9568b2da
  Fix Atari Roms Download (#164) Antonin RAFFIN 2023-03-12 19:06:23 +0100
• 728c1c5b7f
  Issue forms and pyproject.toml (#162) Antonin RAFFIN 2023-03-11 22:57:45 +0100
• 376d9551de
  Update MaskablePPO docs (#150) Alex Pasquali 2023-02-13 14:31:49 +0100
• 6bc8e426bf
  Removed shared layers in mlp_extractor (#137) Alex Pasquali 2023-01-25 16:28:27 +0100
• 1d0edd2dab
  Move pytype to pyproject.toml Antonin Raffin 2023-01-10 22:55:12 +0100
• 7bf9cf3f3a
  Release v1.7.0 (#134) Antonin RAFFIN 2023-01-10 22:35:18 +0100
• b5aa9a47ce
  Deprecation of shared layers in `mlp_extractor` (#133) Alex Pasquali 2023-01-05 10:42:22 +0100
• 7c4a249fa4
  Standardize the use of ``from gym import spaces`` (#131) Quentin Gallouédec 2023-01-02 15:35:00 +0100
• c9bd045d5c
  Add support for python3.10 (#129) Quentin Gallouédec 2022-12-23 00:54:35 +0100
• 9cf8b5076f
  Construct tensors directly on GPUs (#128) Quentin Gallouédec 2022-12-23 00:44:25 +0100
• ab8684f469
  [Feature] Non-shared features extractor in on-policy algorithms (#130) Alex Pasquali 2022-12-23 00:23:45 +0100
• 6b23c6cfe3
  Add `with_bias` parameter to `ARSPolicy` and fix `sb3_contrib/ars/policies.py` type hint (#122) Quentin Gallouédec 2022-12-12 13:22:09 +0100
• 9a728513da
  Upgrade CI/github-actions (#125) Quentin Gallouédec 2022-12-09 12:30:22 +0100
• ddb3a1355e
  Expose modules in `__init__.py` with `__all__` attribute (#124) Zikang Xiong 2022-12-05 09:53:57 -0500
• b3e4ddd09a
  Fix `sb3_contrib/common/recurrent/type_aliases.py` type hint (#121) Quentin Gallouédec 2022-11-29 10:41:07 +0100
• ded9f65bfd
  Fix `sb3_contrib/common/utils.py` type hint (#120) Quentin Gallouédec 2022-11-29 10:24:44 +0100
• 3d28d1e5de
  Mypy type checking (#119) Quentin Gallouédec 2022-11-28 23:00:31 +0100
• 703fd2dd68
  Fix for new flake8 version Antonin Raffin 2022-11-25 18:51:34 +0100
• 36aeae18b5
  Fix `Self` return type (#116) Quentin Gallouédec 2022-11-22 13:12:35 +0100
• a9735b9f31
  Fix reshape LSTM states (#112) Antonin RAFFIN 2022-10-26 18:03:45 +0200
• c75ad7dd58
  Remove deprecated features (#108) Antonin RAFFIN 2022-10-11 13:04:18 +0200
• 52795a307e
  Add progress bar argument (#107) Antonin RAFFIN 2022-10-10 18:44:13 +0200
• e9c97948c8
  Fixed the return type of ``.load()`` methods (#106) Quentin Gallouédec 2022-10-10 17:21:38 +0200
• dec7b5303a
  Deprecate ``create_eval_env``, ``eval_env`` and ``eval_freq`` parameter (#105) Quentin Gallouédec 2022-10-10 17:12:40 +0200
• 2490468b11
  Release v1.6.1 (#104) Antonin RAFFIN 2022-09-29 12:30:12 +0200
• cad9034fdb
  Handle batch norm in target update (#99) Honglu Fan 2022-08-27 04:31:00 -0600
• 7993b75781
  Support `device="auto"`for buffers and set it as default value (#98) Quentin Gallouédec 2022-08-24 09:48:18 +0200
• 049f5a16e9
  Fixed missing verbose parameter passing (#97) Burak Demirbilek 2022-08-16 16:54:46 +0300
• eb48fec638
  Maskable eval callback call callback fix (#93) CppMaster 2022-07-27 19:52:07 +0200
• fc68af8841
  Fixed shared_lstm argument in CNN and MultiInput Policies for RecurrentPPO (#90) Max Lodel 2022-07-26 00:27:17 +0200
• 7e687ac47c
  Use higher resolution time_ns() and avoid division by zero (#91) Adam Gleave 2022-07-25 14:12:20 -0700
• 3cbd2429be
  Fix returned type in predict (#88) Quentin Gallouédec 2022-07-18 11:49:03 +0200
• c9d621b816
  Use ICRL url for PPO blog post Antonin Raffin 2022-07-12 23:49:26 +0200
• 5ec9e01b44
  Update changelog Antonin Raffin 2022-07-12 23:15:14 +0200
• 087951d34b
  Release v1.6.0 and bug fix for TRPO (#84) Antonin RAFFIN 2022-07-12 23:12:24 +0200
• db4c0114d0
  Update default TQC net arch when using NatureCnn (#79) Antonin RAFFIN 2022-06-18 10:53:29 +0200
• bfa86ce4fe
  Fix masked quantities in RecurrentPPO (#78) rnederstigt 2022-06-13 16:00:40 +0200
• 75b2de1399
  Recurrent PPO (#53) Antonin RAFFIN 2022-05-29 22:31:12 -0400
• cd592a111f
  Upgrade min SB3 version (#70) Antonin RAFFIN 2022-05-29 15:54:23 -0400
• bec00386d1
  Upgrade to python 3.7+ syntax (#69) Antonin RAFFIN 2022-04-25 13:02:07 +0200
• 812648e6cd
  Rename QRDQN logger key (#67) Antonin RAFFIN 2022-04-12 12:50:35 +0200
• 99853265a9
  Using policy_aliases instead of register_policy (#66) Grégoire Passault 2022-04-08 15:36:23 -0400
• 9d7e33d213
  Release v1.5.0 (#64) Antonin RAFFIN 2022-03-25 15:04:53 +0100
• f5c1aaa194
  Allow PPO to turn off advantage normalization (#61) Costa Huang 2022-02-23 04:11:16 -0500
• 901a648507
  Upgrade Gym to 0.21 (#59) Adam Gleave 2022-02-22 15:25:43 +0000
• a78891bd00
  Update release date Antonin Raffin 2022-01-19 13:52:30 +0100
• 89f2bae9f6
  Release 1.4.0 (#57) Antonin RAFFIN 2022-01-19 13:50:56 +0100
• 675304d8fa
  Augmented Random Search (ARS) (#42) Sean Gillen 2022-01-18 04:57:27 -0800
• 3b007ae93b
  Fix TRPO doc Antonin Raffin 2021-12-29 15:03:51 +0100
• 59be198da0
  Add Trust Region Policy Optimization (TRPO) (#40) Cyprien 2021-12-29 10:58:03 +0000
• b44689b0ea
  Update Maskable PPO to match SB3 PPO + improve coverage (#56) Antonin RAFFIN 2021-12-10 12:48:19 +0100
• 20b5351086
  Add color in the tests Antonin Raffin 2021-12-10 12:38:40 +0100
• 833669a88b
  Drop python 3.6 support (#55) Antonin RAFFIN 2021-12-06 12:59:53 +0100
• a1b5ea67ae
  Multiprocessing support for off policy algorithms (#50) Antonin RAFFIN 2021-12-02 10:40:21 +0100
• cd0a5e516f
  Update citation (#54) Antonin RAFFIN 2021-12-01 19:09:32 +0100
• b1397bbb72
  Release 1.3.0 (#48) Antonin RAFFIN 2021-10-23 17:21:22 +0200
• d6c5cea644
  MaskablePPO dictionary observation support (#47) Geoff McDonald 2021-10-23 08:05:37 -0700
• 91f9b1ed34
  Remove sde net arch (#44) Antonin RAFFIN 2021-09-28 21:59:59 +0200
• c525c5107b Upgrade min sphinx version Antonin Raffin 2021-09-23 15:26:37 +0200
• ab24f8039f
  PPO variant with invalid action masking (#25) kronion 2021-09-23 07:50:10 -0500
• b2e7126840
  Train/Eval Mode Support (#39) Scott Brownlie 2021-09-08 11:54:50 +0100
• 36eca8ee79
  Fix type annotation + add python 3.9 + citation (#37) Antonin RAFFIN 2021-07-29 18:14:03 +0200