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

12 Commits

Author SHA1 Message Date
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
Zikang Xiong ddb3a1355e
Expose modules in `__init__.py` with `__all__` attribute (#124) 
* expose modules in __init__.py with __all__ attribute

* Update version

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
 2022-12-05 15:53:57 +01:00
Quentin Gallouédec 36aeae18b5
Fix `Self` return type (#116) 
* Self hint for distributions

* ClassSelf to SelfClass
 2022-11-22 13:12:35 +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
Antonin RAFFIN 52795a307e
Add progress bar argument (#107) 
* Add progress bar argument

* Sort imports
 2022-10-10 18:44:13 +02:00
Quentin Gallouédec e9c97948c8
Fixed the return type of ``.load()`` methods (#106) 
* Fix return type for learn using TypeVar

* Update changelog

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
 2022-10-10 17:21:38 +02:00
Quentin Gallouédec dec7b5303a
Deprecate ``create_eval_env``, ``eval_env`` and ``eval_freq`` parameter (#105) 
* Deprecate ``eval_env``, ``eval_freq```and ``create_eval_env``

* Update changelog

* Typo

* Raise deprecation warining in _setup_learn

* Upgrade to latest SB3 version and update changelog

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
 2022-10-10 17:12:40 +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
rnederstigt bfa86ce4fe
Fix masked quantities in RecurrentPPO (#78) 
* Ignore masked indexes when calculating the loss functions
 2022-06-13 16:00:40 +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