saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-07-30 20:18:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix arguments order of explained_variance() (#227)

Browse source 
* Fix for arguments order in explained_variance()

Fix for arguments order in explained_variance() in PPO

* Fix for arguments order in explained_variance()

Fix for arguments order in explained_variance() in a2c

* Fix for arguments order in explained_variance()

update changelog.rst
This commit is contained in:
thisray 2020-11-16 23:27:46 +08:00 committed by GitHub
parent 18d10dbf42
commit 5ddda44a74
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

3
docs/misc/changelog.rst
View file

@ -27,6 +27,7 @@ New Features:
Bug Fixes:
^^^^^^^^^^
- Fixed bug where code added VecTranspose on channel-first image environments (thanks @qxcv)
- Fixed bug that the arguments order of ``explained_variance()`` in ``ppo.py`` and ``a2c.py`` is not correct (@thisray)
Deprecations:
^^^^^^^^^^^^^
@ -515,4 +516,4 @@ And all the contributors:
@MarvineGothic @jdossgollin @stheid @SyllogismRXS @rusu24edward @jbulow @Antymon @seheevic @justinkterry @edbeeching
@flodorner @KuKuXia @NeoExtended @PartiallyTyped @mmcenta @richardwu @kinalmehta @rolandgvc @tkelestemur @mloo3
@tirafesi @blurLake @koulakis @joeljosephjin @shwang @rk37 @andyshih12 @RaphaelWag @xicocaio
@diditforlulz273 @liorcohen5 @ManifoldFR @mloo3 @SwamyDev @wmmc88 @megan-klaiber
@diditforlulz273 @liorcohen5 @ManifoldFR @mloo3 @SwamyDev @wmmc88 @megan-klaiber @thisray

2
stable_baselines3/a2c/a2c.py
View file

@ -156,7 +156,7 @@ class A2C(OnPolicyAlgorithm):
th.nn.utils.clip_grad_norm_(self.policy.parameters(), self.max_grad_norm)
self.policy.optimizer.step()
explained_var = explained_variance(self.rollout_buffer.returns.flatten(), self.rollout_buffer.values.flatten())
explained_var = explained_variance(self.rollout_buffer.values.flatten(), self.rollout_buffer.returns.flatten())
self._n_updates += 1
logger.record("train/n_updates", self._n_updates, exclude="tensorboard")

2
stable_baselines3/ppo/ppo.py
View file

@ -220,7 +220,7 @@ class PPO(OnPolicyAlgorithm):
break
self._n_updates += self.n_epochs
explained_var = explained_variance(self.rollout_buffer.returns.flatten(), self.rollout_buffer.values.flatten())
explained_var = explained_variance(self.rollout_buffer.values.flatten(), self.rollout_buffer.returns.flatten())
# Logs
logger.record("train/entropy_loss", np.mean(entropy_losses))