From 9b42b9717a6987b651eebd8377bbe9c71012b5d0 Mon Sep 17 00:00:00 2001 From: Antonin RAFFIN Date: Sun, 24 May 2020 16:44:44 +0200 Subject: [PATCH] Fix `sde_sample_freq` for SAC (#32) * Fix `sde_sample_freq` for SAC * [ci skip] Add Acknowledgments --- README.md | 6 ++++++ docs/misc/changelog.rst | 3 ++- stable_baselines3/common/base_class.py | 2 +- stable_baselines3/version.txt | 2 +- 4 files changed, 10 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 7031d9f..f8d5b27 100644 --- a/README.md +++ b/README.md @@ -227,5 +227,11 @@ Stable-Baselines3 is currently maintained by [Ashley Hill](https://github.com/hi To any interested in making the baselines better, there is still some documentation that needs to be done. If you want to contribute, please read [**CONTRIBUTING.md**](./CONTRIBUTING.md) guide first. +## Acknowledgments + +The initial work to develop Stable Baselines3 was partially funded by the project *Reduced Complexity Models* from the *Helmholtz-Gemeinschaft Deutscher Forschungszentren*. + +The original version, Stable Baselines, was created in the [robotics lab U2IS](http://u2is.ensta-paristech.fr/index.php?lang=en) ([INRIA Flowers](https://flowers.inria.fr/) team) at [ENSTA ParisTech](http://www.ensta-paristech.fr/en). + Logo credits: [L.M. Tenkes](https://www.instagram.com/lucillehue/) diff --git a/docs/misc/changelog.rst b/docs/misc/changelog.rst index cd87dd9..e28e9c4 100644 --- a/docs/misc/changelog.rst +++ b/docs/misc/changelog.rst @@ -3,7 +3,7 @@ Changelog ========== -Pre-Release 0.6.0a9 (WIP) +Pre-Release 0.6.0a10 (WIP) ------------------------------ Breaking Changes: @@ -24,6 +24,7 @@ Bug Fixes: - Fixed a bug that prevented model trained on cpu to be loaded on gpu - Fixed version number that had a new line included - Fixed weird seg fault in docker image due to FakeImageEnv by reducing screen size +- Fixed ``sde_sample_freq`` that was not taken into account for SAC Deprecations: ^^^^^^^^^^^^^ diff --git a/stable_baselines3/common/base_class.py b/stable_baselines3/common/base_class.py index 10ac9f8..a2405d6 100644 --- a/stable_baselines3/common/base_class.py +++ b/stable_baselines3/common/base_class.py @@ -798,7 +798,7 @@ class OffPolicyRLModel(BaseRLModel): while not done: - if self.use_sde and self.sde_sample_freq > 0 and n_steps % self.sde_sample_freq == 0: + if self.use_sde and self.sde_sample_freq > 0 and total_steps % self.sde_sample_freq == 0: # Sample a new noise matrix self.actor.reset_noise() diff --git a/stable_baselines3/version.txt b/stable_baselines3/version.txt index 21c9503..e2e4bb2 100644 --- a/stable_baselines3/version.txt +++ b/stable_baselines3/version.txt @@ -1 +1 @@ -0.6.0a9 +0.6.0a10