mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-11-17 08:56:08 +00:00
Release v1.7.0 (#1268)
This commit is contained in:
parent
5aa6e7d340
commit
6b8905acdb
2 changed files with 4 additions and 4 deletions
|
|
@ -4,7 +4,7 @@ Changelog
|
||||||
==========
|
==========
|
||||||
|
|
||||||
|
|
||||||
Release 1.7.0a12 (WIP)
|
Release 1.7.0 (2023-01-10)
|
||||||
--------------------------
|
--------------------------
|
||||||
|
|
||||||
.. warning::
|
.. warning::
|
||||||
|
|
@ -53,7 +53,7 @@ New Features:
|
||||||
|
|
||||||
Bug Fixes:
|
Bug Fixes:
|
||||||
^^^^^^^^^^
|
^^^^^^^^^^
|
||||||
- Updated ``ProgressBarCallback`` to more accurately display the proportion of remaining timesteps (@dominicgkerr)
|
- Fixed ``ProgressBarCallback`` under-reporting (@dominicgkerr)
|
||||||
- Fixed return type of ``evaluate_actions`` in ``ActorCritcPolicy`` to reflect that entropy is an optional tensor (@Rocamonde)
|
- Fixed return type of ``evaluate_actions`` in ``ActorCritcPolicy`` to reflect that entropy is an optional tensor (@Rocamonde)
|
||||||
- Fixed type annotation of ``policy`` in ``BaseAlgorithm`` and ``OffPolicyAlgorithm``
|
- Fixed type annotation of ``policy`` in ``BaseAlgorithm`` and ``OffPolicyAlgorithm``
|
||||||
- Allowed model trained with Python 3.7 to be loaded with Python 3.8+ without the ``custom_objects`` workaround
|
- Allowed model trained with Python 3.7 to be loaded with Python 3.8+ without the ``custom_objects`` workaround
|
||||||
|
|
|
||||||
|
|
@ -1 +1 @@
|
||||||
1.7.0a12
|
1.7.0
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue