stable-baselines3/stable_baselines3/ppo
Hugh Perkins 2cc1477fa2
Fix advantage normalization with mini-batchsize of 1 (#1028)
* fix nan in advnatages with batch size 1, for ppo

* changelog

* black

* Simplify test

* Bump version

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
2022-08-25 11:50:08 +02:00
..
__init__.py Dictionary Observations (#243) 2021-05-11 12:29:30 +02:00
policies.py Replacing the policy registry with policy "aliases" (#842) 2022-04-08 21:21:53 +02:00
ppo.py Fix advantage normalization with mini-batchsize of 1 (#1028) 2022-08-25 11:50:08 +02:00