Skip to content
/ CCQD Public

Official implementation of ICLR'24 spotlight paper "Sample-Efficient Quality-Diversity by Cooperative Coevolution".

License

Notifications You must be signed in to change notification settings

lamda-bbo/CCQD

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Sample-Efficient Quality-Diversity by Cooperative Coevolution

The official implementation of our ICLR'24 paper Sample-Efficient Quality-Diversity by Cooperative Coevolution.

Requirements

The implementation is built in conda.

The environment can be built with

conda env create -f environment.yml

Running Experiments

Run the following commands to evaluate CCQD on Humanoid Uni:

conda activate ccqd
python -m src algo=CCQD env=humanoid_uni seed=1000

You can replace each of the three parameters (i.e., algo, env, and seed) to evaluate different methods on different environments with different seeds.

License

The code is licensed under the MIT License.

Citation

@inproceedings{CCQD,
    author = {Ke Xue and Ren-Jian Wang and Pengyi Li and Dong Li and Jianye Hao and Chao Qian},
    title = {Sample-Efficient Quality-Diversity by Cooperative Coevolution},
    booktitle = {Proceedings of the 12th International Conference on Learning Representations (ICLR'24)},
    year = {2024},
    address = {Vienna, Austria},
}

About

Official implementation of ICLR'24 spotlight paper "Sample-Efficient Quality-Diversity by Cooperative Coevolution".

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages