Release 1.4.0 (#729)

* Release 1.4.0

* Add integration section in the readme
This commit is contained in:
Antonin RAFFIN 2022-01-19 11:16:15 +01:00 committed by GitHub
parent cd6e04705b
commit 21f6a474a4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 19 additions and 2 deletions

View file

@ -49,6 +49,11 @@ A migration guide from SB2 to SB3 can be found in the [documentation](https://st
Documentation is available online: [https://stable-baselines3.readthedocs.io/](https://stable-baselines3.readthedocs.io/) Documentation is available online: [https://stable-baselines3.readthedocs.io/](https://stable-baselines3.readthedocs.io/)
## Integrations
Stable-Baselines3 has some integration with other libraries/services like Weights & Biases for experiment tracking or Hugging Face for storing/sharing trained models. You can find out more in the [dedicated section](https://stable-baselines3.readthedocs.io/en/master/guide/integrations.html) of the documentation.
## RL Baselines3 Zoo: A Training Framework for Stable Baselines3 Reinforcement Learning Agents ## RL Baselines3 Zoo: A Training Framework for Stable Baselines3 Reinforcement Learning Agents
[RL Baselines3 Zoo](https://github.com/DLR-RM/rl-baselines3-zoo) is a training framework for Reinforcement Learning (RL). [RL Baselines3 Zoo](https://github.com/DLR-RM/rl-baselines3-zoo) is a training framework for Reinforcement Learning (RL).

View file

@ -4,9 +4,11 @@ Changelog
========== ==========
Release 1.3.1a9 (WIP) Release 1.4.0 (2022-01-18)
--------------------------- ---------------------------
*TRPO, ARS and multi env training for off-policy algorithms*
Breaking Changes: Breaking Changes:
^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^
- Dropped python 3.6 support (as announced in previous release) - Dropped python 3.6 support (as announced in previous release)
@ -15,6 +17,15 @@ Breaking Changes:
this may affect custom callbacks. this may affect custom callbacks.
- Removed ``episode_reward`` field from ``RolloutReturn()`` type - Removed ``episode_reward`` field from ``RolloutReturn()`` type
.. warning::
An update to the ``HER`` algorithm is planned to support multi-env training and remove the max episode length constrain.
(see `PR #704 <https://github.com/DLR-RM/stable-baselines3/pull/704>`_)
This will be a backward incompatible change (model trained with previous version of ``HER`` won't work with the new version).
New Features: New Features:
^^^^^^^^^^^^^ ^^^^^^^^^^^^^
- Added ``norm_obs_keys`` param for ``VecNormalize`` wrapper to configure which observation keys to normalize (@kachayev) - Added ``norm_obs_keys`` param for ``VecNormalize`` wrapper to configure which observation keys to normalize (@kachayev)
@ -27,6 +38,7 @@ SB3-Contrib
^^^^^^^^^^^ ^^^^^^^^^^^
- Added Trust Region Policy Optimization (TRPO) (@cyprienc) - Added Trust Region Policy Optimization (TRPO) (@cyprienc)
- Added Augmented Random Search (ARS) (@sgillen) - Added Augmented Random Search (ARS) (@sgillen)
- Coming soon: PPO LSTM, see https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/pull/53
Bug Fixes: Bug Fixes:
^^^^^^^^^^ ^^^^^^^^^^

View file

@ -1 +1 @@
1.3.1a9 1.4.0