saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-09-17 22:30:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix PPO logging of clip_fractions (#150)

Browse source 
* bugfix for PPO logging of clip_fractions

* Update changelog.rst

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
This commit is contained in:
Vsevolod Kompantsev 2020-09-01 10:52:31 +03:00 committed by GitHub
parent f8c25d3b71
commit 4fd408bec2
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/misc/changelog.rst
View file

@ -18,6 +18,7 @@ New Features:
Bug Fixes: Bug Fixes:
^^^^^^^^^^ ^^^^^^^^^^
- Fixed a bug where the environment was reset twice when using ``evaluate_policy`` - Fixed a bug where the environment was reset twice when using ``evaluate_policy``
- Fix logging of ``clip_fraction`` in PPO (@diditforlulz273)
Deprecations: Deprecations:
^^^^^^^^^^^^^ ^^^^^^^^^^^^^
@ -398,3 +399,4 @@ And all the contributors:
@MarvineGothic @jdossgollin @SyllogismRXS @rusu24edward @jbulow @Antymon @seheevic @justinkterry @edbeeching @MarvineGothic @jdossgollin @SyllogismRXS @rusu24edward @jbulow @Antymon @seheevic @justinkterry @edbeeching
@flodorner @KuKuXia @NeoExtended @PartiallyTyped @mmcenta @richardwu @kinalmehta @rolandgvc @tkelestemur @mloo3 @flodorner @KuKuXia @NeoExtended @PartiallyTyped @mmcenta @richardwu @kinalmehta @rolandgvc @tkelestemur @mloo3
@tirafesi @blurLake @koulakis @joeljosephjin @shwang @rk37 @andyshih12 @RaphaelWag @xicocaio @tirafesi @blurLake @koulakis @joeljosephjin @shwang @rk37 @andyshih12 @RaphaelWag @xicocaio
@diditforlulz273

2
stable_baselines3/ppo/ppo.py
View file

@ -228,7 +228,7 @@ class PPO(OnPolicyAlgorithm):
logger.record("train/policy_gradient_loss", np.mean(pg_losses)) logger.record("train/policy_gradient_loss", np.mean(pg_losses))
logger.record("train/value_loss", np.mean(value_losses)) logger.record("train/value_loss", np.mean(value_losses))
logger.record("train/approx_kl", np.mean(approx_kl_divs)) logger.record("train/approx_kl", np.mean(approx_kl_divs))
logger.record("train/clip_fraction", np.mean(clip_fraction)) logger.record("train/clip_fraction", np.mean(clip_fractions))
logger.record("train/loss", loss.item()) logger.record("train/loss", loss.item())
logger.record("train/explained_variance", explained_var) logger.record("train/explained_variance", explained_var)
if hasattr(self.policy, "log_std"): if hasattr(self.policy, "log_std"):