OscervaME
/
stable-baselines3-contrib-sacd
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
117 Commits 1 Branch 0 Tags 1.1 MiB
Commit Graph

13 Commits

Author SHA1 Message Date
Antonin RAFFIN 728c1c5b7f
Issue forms and pyproject.toml (#162) 
* Issue forms and pyproject.toml

* [ci skip] Fix typos

* Fix isort config

* Use secret link to download atari roms

* Fix for mypy and update config

* Upgrade SB3 and fix warnings

* Fix doc build

* Update Makefile

* Lint first
 2023-03-11 22:57:45 +01:00
Alex Pasquali 6bc8e426bf
Removed shared layers in mlp_extractor (#137) 
* Removed shared layers in mlp_extractor

* Add ruff

* Update version and add warning

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
 2023-01-25 16:28:27 +01:00
Alex Pasquali b5aa9a47ce
Deprecation of shared layers in `mlp_extractor` (#133) 
* Deprecation of shared layers in mlp_extractor

* Fix missing import

* Reformat and update tests

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
 2023-01-05 10:42:22 +01:00
Quentin Gallouédec 7c4a249fa4
Standardize the use of ``from gym import spaces`` (#131) 
* Standardize from gym import spaces

* update changelog

* update issue template

* update version

* Update version
 2023-01-02 15:35:00 +01:00
Quentin Gallouédec 9cf8b5076f
Construct tensors directly on GPUs (#128) 
* `to(device)` to `device=device` and `float()` to `dtype=th.float32`

* Update changelog

* Fix type checking

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
 2022-12-23 00:44:25 +01:00
Alex Pasquali ab8684f469
[Feature] Non-shared features extractor in on-policy algorithms (#130) 
* Modified sb3_contrib/common/maskable/policies.py

- Added support for non-shared features extractor in file sb3_contrib/common/maskable/policies.py
- updated changelog

* Modified sb3_contrib/common/recurrent/policies.py

* Modified sb3_contrib/qrdqn/policies.py and sb3_contrib/tqc/policies.py

* Updated test_cnn.py

* Upgrade SB3 version

* Revert changes in formatting

* Remove duplicate normalize_images

* Add test for image-like inputs

* Fixes and add more tests

* Update SB3 version

* Fix ARS warnings

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
 2022-12-23 00:23:45 +01:00
Quentin Gallouédec b3e4ddd09a
Fix `sb3_contrib/common/recurrent/type_aliases.py` type hint (#121) 
* Update setup.cfg

* Update changelog

* Update type aliases
 2022-11-29 10:41:07 +01:00
Antonin RAFFIN a9735b9f31
Fix reshape LSTM states (#112) 
* Fix LSTM states reshape

* Fix warnings and update changelog

* Remove unused variable

* Fix runtime error when using n_lstm_layers > 1
 2022-10-26 18:03:45 +02:00
Antonin RAFFIN c75ad7dd58
Remove deprecated features (#108) 
* Remove deprecated features

* Upgrade SB3

* Fix tests
 2022-10-11 13:04:18 +02:00
Quentin Gallouédec 7993b75781
Support `device="auto"`for buffers and set it as default value (#98) 
* Default device for buffer is auto

* `device=auto` in ARS

* Undo ARS change

* Update changelog

* Update min SB3 version

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
 2022-08-24 09:48:18 +02:00
Max Lodel fc68af8841
Fixed shared_lstm argument in CNN and MultiInput Policies for RecurrentPPO (#90) 
* fixed shared_lstm parameter in CNN and MultiInput Policies

* updated tests

* changelog

* Fix FPS for recurrent PPO

* Fix import

* Update changelog

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
 2022-07-26 00:27:17 +02:00
Quentin Gallouédec 3cbd2429be
Fix returned type in predict (#88) 
* actions[0] -> actions.squeeze(0)

* Update changelog

* Update changelog

* Update version

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
 2022-07-18 11:49:03 +02:00
Antonin RAFFIN 75b2de1399
Recurrent PPO (#53) 
* Running (not working yet) version of recurrent PPO

* Fixes for multi envs

* Save WIP, rework the sampling

* Add Box support

* Fix sample order

* Being cleanup, code is broken (again)

* First working version (no shared lstm)

* Start cleanup

* Try rnn with value function

* Re-enable batch size

* Deactivate vf rnn

* Allow any batch size

* Add support for evaluation

* Add CNN support

* Fix start of sequence

* Allow shared LSTM

* Rename mask to episode_start

* Fix type hint

* Enable LSTM for critic

* Clean code

* Fix for CNN LSTM

* Fix sampling with n_layers > 1

* Add std logger

* Update wording

* Rename and add dict obs support

* Fixes for dict obs support

* Do not run slow tests

* Fix doc

* Update recurrent PPO example

* Update README

* Use Pendulum-v1 for tests

* Fix image env

* Speedup LSTM forward pass (#63)

* added more efficient lstm implementation

* Rename and add comment

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>

* Fixes

* Remove OpenAI sampling and improve coverage

* Sync with SB3 PPO

* Pass state shape and allow lstm kwargs

* Update tests

* Add masking for padded sequences

* Update default in perf test

* Remove TODO, mask is now working

* Add helper to remove duplicated code, remove hack for padding

* Enable LSTM critic and raise threshold for cartpole with no vel

* Fix tests

* Update doc and tests

* Doc fix

* Fix for new Sphinx version

* Fix doc note

* Switch to batch first, no more additional swap

* Add comments and mask entropy loss

Co-authored-by: Neville Walo <43504521+Walon1998@users.noreply.github.com>
 2022-05-30 04:31:12 +02:00