saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-06-29 03:31:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Doc fix: A2C - fix guidance on RMSpropTFLike (#708)

Browse source 
* doc: A2C/migration: fix guidance on RMSpropTFLike

* Update changelog.rst

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
This commit is contained in:
Thomas Gubler 2021-12-30 11:28:12 +01:00 committed by GitHub
parent 4a5dfaedfc
commit c895c1d46f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 4 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/guide/migration.rst
View file

@ -113,7 +113,7 @@ A2C
PyTorch implementation of RMSprop `differs from Tensorflow's <https://github.com/pytorch/pytorch/issues/23796>`_,
which leads to `different and potentially more unstable results <https://github.com/DLR-RM/stable-baselines3/pull/110#issuecomment-663255241>`_.
Use ``stable_baselines3.common.sb2_compat.rmsprop_tf_like.RMSpropTFLike`` optimizer to match the results
with TensorFlow's implementation. This can be done through ``policy_kwargs``: ``A2C(policy_kwargs=dict(optimizer_class=RMSpropTFLike, eps=1e-5))``
with TensorFlow's implementation. This can be done through ``policy_kwargs``: ``A2C(policy_kwargs=dict(optimizer_class=RMSpropTFLike, optimizer_kwargs=dict(eps=1e-5)))``
PPO

3
docs/misc/changelog.rst
View file

@ -54,6 +54,7 @@ Documentation:
- Updated ``BaseAlgorithm.load`` docstring (@Demetrio92)
- Added a note on ``load`` behavior in the examples (@Demetrio92)
- Updated SB3 Contrib doc
- Fixed A2C and migration guide guidance on how to set epsilon with RMSpropTFLike (@thomasgubler)
Release 1.3.0 (2021-10-23)
---------------------------
@ -858,4 +859,4 @@ And all the contributors:
@ShangqunYu @PierreExeter @JacopoPan @ltbd78 @tom-doerr @Atlis @liusida @09tangriro @amy12xx @juancroldan
@benblack769 @bstee615 @c-rizz @skandermoalla @MihaiAnca13 @davidblom603 @ayeright @cyprienc
@wkirgsn @AechPro @CUN-bjy @batu @IljaAvadiev @timokau @kachayev @cleversonahum
@eleurent @ac-93 @cove9988 @theDebugger811 @hsuehch @Demetrio92
@eleurent @ac-93 @cove9988 @theDebugger811 @hsuehch @Demetrio92 @thomasgubler

2
docs/modules/a2c.rst
View file

@ -14,7 +14,7 @@ It uses multiple workers to avoid the use of a replay buffer.
If you find training unstable or want to match performance of stable-baselines A2C, consider using
``RMSpropTFLike`` optimizer from ``stable_baselines3.common.sb2_compat.rmsprop_tf_like``.
You can change optimizer with ``A2C(policy_kwargs=dict(optimizer_class=RMSpropTFLike, eps=1e-5))``.
You can change optimizer with ``A2C(policy_kwargs=dict(optimizer_class=RMSpropTFLike, optimizer_kwargs=dict(eps=1e-5)))``.
Read more `here <https://github.com/DLR-RM/stable-baselines3/pull/110#issuecomment-663255241>`_.