From 6b8905acdb27e7b2acd036efc918818cc7ee3e20 Mon Sep 17 00:00:00 2001 From: Antonin RAFFIN Date: Tue, 10 Jan 2023 17:32:57 +0100 Subject: [PATCH] Release v1.7.0 (#1268) --- docs/misc/changelog.rst | 6 +++--- stable_baselines3/version.txt | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/misc/changelog.rst b/docs/misc/changelog.rst index 7374f906e..aac76a5db 100644 --- a/docs/misc/changelog.rst +++ b/docs/misc/changelog.rst @@ -4,11 +4,11 @@ Changelog ========== -Release 1.7.0a12 (WIP) +Release 1.7.0 (2023-01-10) -------------------------- .. warning:: - + Shared layers in MLP policy (``mlp_extractor``) are now deprecated for PPO, A2C and TRPO. This feature will be removed in SB3 v1.8.0 and the behavior of ``net_arch=[64, 64]`` will create **separate** networks with the same architecture, to be consistent with the off-policy algorithms. @@ -53,7 +53,7 @@ New Features: 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 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 diff --git a/stable_baselines3/version.txt b/stable_baselines3/version.txt index 77ca7d320..bd8bf882d 100644 --- a/stable_baselines3/version.txt +++ b/stable_baselines3/version.txt @@ -1 +1 @@ -1.7.0a12 +1.7.0