Skip to content

[CoRL2022] Source code for "Efficient and Stable Off-policy Training via Behavior-aware Evolutionary Learning"

License

Notifications You must be signed in to change notification settings

raymond-myc/BEL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Code for "Efficient and Stable Off-policy Training via Behavior-aware Evolutionary Learning" accepted by CoRL2022.

Usage

It is straight forward to run BEL in a local conda environment. First make sure you have mujoco200 and mjkey.txt in your ~/.mujoco. Then create the conda env and run bel.py. By default, experiment's logs will be output to a directory called results.

conda env create -f environment.yml
conda activate bel
python bel.py --env_name Ant-v3 --seed 10

About

[CoRL2022] Source code for "Efficient and Stable Off-policy Training via Behavior-aware Evolutionary Learning"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages