saymrwulf/stable-baselines3
1
0
Fork 0
mirror of https://github.com/saymrwulf/stable-baselines3.git synced 2026-06-05 00:00:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
stable-baselines3/stable_baselines3
History
Julio César Alves cdaa9ab418
Callback to early stop the training if there is no model improvement after consecutive evaluations (#741) 
* Added StopTrainingOnNoModelImprovement callback and callback_after_eval parameter in EvalCallback

* Correction in EvalCallback and tests for StopTrainingOnNoModelImprovement

* Update the docs related to new StopTrainingOnNoModelImprovement callback

* Update doc

Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
Co-authored-by: Antonin Raffin <antonin.raffin@dlr.de>
2022-02-25 11:56:47 +01:00
..
a2c Add timeout handling for on-policy algorithms (#658) 2021-11-16 17:19:16 +01:00
common Callback to early stop the training if there is no model improvement after consecutive evaluations (#741) 2022-02-25 11:56:47 +01:00
ddpg System info helper (#613) 2021-10-18 10:43:56 +02:00
dqn None as default value for env in HerReplayBuffer.sample + DQN batch size typing fix (#790) 2022-02-24 15:51:01 +01:00
her None as default value for env in HerReplayBuffer.sample + DQN batch size typing fix (#790) 2022-02-24 15:51:01 +01:00
ppo Allow PPO to turn off advantage normalization (#763) 2022-02-22 15:29:21 +01:00
sac Remove explict forward calls (#753) 2022-02-06 22:27:12 +02:00
td3 Remove explict forward calls (#753) 2022-02-06 22:27:12 +02:00
__init__.py System info helper (#613) 2021-10-18 10:43:56 +02:00
py.typed Rename to stable-baselines3 2020-05-05 15:02:35 +02:00
version.txt Fix normalization for DictReplayBuffer (#744) 2022-02-23 13:04:57 +01:00