stable-baselines3/stable_baselines3
Mark Smith 9a749389d3
Cast learning_rate to float lambda for pickle safety when doing model.load (#1901)
* create failing test for unpickle error

* Fix learning_rate argument causing failure in weights_only=True if passed a function with non-float types

* Updated with feedback from araffin on PR#1901

* Update test and version

* Update changelog and SBX doc

---------

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
2024-04-22 10:04:01 +02:00
..
a2c Add rollout_buffer_class parameter to on-policy algorithms (#1720) 2023-10-27 17:36:24 +02:00
common Cast learning_rate to float lambda for pickle safety when doing model.load (#1901) 2024-04-22 10:04:01 +02:00
ddpg Update TD3/DDPG/DQN defaults for consistency (#1785) 2024-01-12 16:05:14 +01:00
dqn Update TD3/DDPG/DQN defaults for consistency (#1785) 2024-01-12 16:05:14 +01:00
her Fix type annotations of buffers (#1700) 2023-09-28 18:52:46 +02:00
ppo Add rollout_buffer_class parameter to on-policy algorithms (#1720) 2023-10-27 17:36:24 +02:00
sac Fix policies type annotations (#1735) 2023-11-06 18:35:28 +01:00
td3 Update TD3/DDPG/DQN defaults for consistency (#1785) 2024-01-12 16:05:14 +01:00
__init__.py Add Gymnasium support (#1327) 2023-04-14 13:13:59 +02:00
py.typed Rename to stable-baselines3 2020-05-05 15:02:35 +02:00
version.txt Cast learning_rate to float lambda for pickle safety when doing model.load (#1901) 2024-04-22 10:04:01 +02:00