saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-06-27 03:11:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
526 commits 18 branches 32 tags 5.2 MiB
Commit graph

9 commits

Author SHA1 Message Date
Antonin RAFFIN
8a08078ea2
Fix default arguments + add bugbear (#363) 
* Fix potential bug + add bug bear

* Remove unused variables

* Minor: version bump
 2021-03-25 11:35:21 +02:00
Anssi
e2b6f5460f
Avoid transposing channel-first envs (#213) 
* Add test for channel-first environments

* Add support for channel-first envs, including more tests

* Update changelog

* Run black

* Run black, again

* Improve NatureCNN error message

* Update image checks and FrameStack wrapper

* Update tests

* Update docs

* Run isort

* Reformat

* Fixes: avoid breaking changes for non-image env

* Add additional checks

* Update docstring

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
 2020-11-03 12:34:09 +01:00
Antonin RAFFIN
0fc0dd1b21
Fix off policy features extractor (#198) 
* Faster tests

* Fix feature extractor bug + add check

* Add missing check

* Allow TD3 features extractor to be separate

* Add share features extractor option for SAC

* Bug fixes

* Apply suggestions from code review

Co-authored-by: Adam Gleave <adam@gleave.me>

Co-authored-by: Adam Gleave <adam@gleave.me>
 2020-10-27 14:24:59 +01:00
Antonin RAFFIN
2599f04940
Add custom arch for off-policy actor/critic networks (#182) 
* Add custom arch for off-policy actor/critic networks

* Fix type hints

* Address comments

* Make sure number of updated parameters match in polyak

* Add zip_strict for strict-length zipping

* Fix building docs

* Add test for zip strict

* Faster tests

Co-authored-by: Anssi "Miffyli" Kanervisto <kaneran21@hotmail.com>
 2020-10-13 12:01:33 +02:00
Antonin RAFFIN
55912576ed
Cleanup docstring types (#169) 
* Cleanup docstring types

* Update style

* Test with js hack

* Revert "Test with js hack"

This reverts commit d091f438e8851ab8d01b66628e06a104f5e5ec69.

* Fix types

* Fix typo

* Update CONTRIBUTING example
 2020-10-02 20:05:55 +03:00
Antonin RAFFIN
2c924f52f5
Update docs (custom policy, type hints) (#167) 
* Change import

* Update custom policy doc

* Re-enable sphinx_autodoc_typehints

* Update docker image

* Attempt to fix read the doc build error

* Add sphinx_autodoc_typehints to read the doc env

* Fix pip version

* Add full custom policy example

* Fix
 2020-09-29 20:41:14 +03:00
Anssi
2cd6a4f93b
Match performance with stable-baselines (discrete case) (#110) 
* Fix storing correct episode dones

* Fix number of filters in NatureCNN network

* Add TF-like RMSprop for matching performance with sb2

* Remove stuff that was accidentally included

* Reformat

* Clarify variable naming

* Update changelog

* Add comment on RMSprop implementations to A2C

* Add test for RMSpropTFLike

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
 2020-08-03 22:22:51 +02:00
Antonin RAFFIN
23afedb254
Auto-formatting with black and isort (#97) 
* Add auto formatting with black and isort

* Reformat code

* Ignore typing errors

* Add note about line length

* Add minimum version for isort

* Add commit-checks

* Update docker image

* Fixed lost import (during last merge)

* Fix opencv dependency
 2020-07-16 16:12:16 +02:00
Anssi
44f8218df0
Review of code (A2C, PPO and refactoring) (#35) 
* Split torch module code into torch_layers file

* Updated reference to CNN

* Change 'CxWxH' to 'CxHxW', as per common notion

* Fix missing import in policies.py

* Move PPOPolicy to OnlineActorCriticPolicy

* Create OnPolicyRLModel from PPO, and make A2C and PPO inherit

* Update A2C optimizer comment

* Clean weight init scales for clarity

* Fix A2C log_interval default parameter

* Rename 'progress' to 'progress_remaining

* Rename 'Models' to 'Algorithms'

* Rename 'OnlineActorCriticPolicy' to 'ActorCriticPolicy'

* Move static functions out from BaseAlgorithm

* Move on/off_policy base algorithms to their own files

* Add  files for A2C/PPO

* Fix docs

* Fix pytype

* Update documentation on OnPolicyAlgorithm

* Add proper doctstring for on_policy rollout gathering

* Add bit clarification on the mlppolicy/cnnpolicy naming

* Move static function is_vectorized_policies to utils.py

* Checking docstrings, pep8 fixes

* Update changelog

* Clean changelog

* Remove policy warnings for sac/td3

* Add monitor_wrapper for OnPolicyAlgorithm. Clean tb logging variables. Add parameter keywords to OffPolicyAlgorithm super init

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
 2020-06-09 13:54:18 +02:00