Stable-Baselines-Team / stable-baselines3-contrib

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
https://sb3-contrib.readthedocs.io
MIT License
504 stars 175 forks source link

Fix reshape LSTM states #112

Closed araffin closed 2 years ago

araffin commented 2 years ago

Description

Context

fixes #111 and fixes some warnings in the tests

@kolbytn could you review that PR?

Types of changes

Checklist:

Note: we are using a maximum length of 127 characters per line