This repository includes the code to replicate the PBAC algorithm from the following publication:
Deep Exploration With PAC-Bayes
Bahareh Tasdighi, Manuel Haussmann, Nicklas Werge, Yi-Shan Wu, Melih Kandemir, 2025
European Conference on Artificial Intelligence
ArXiv
To train the PBAC on dmcartpole swingup environment run the following command:
python main.py
If you use PBAC, please cite:
@inproceedings{tasdighi2025pbac,
title = {Deep Exploration with PAC-Bayes},
author = {Tasdighi, B. and Haussmann, M. and Werge, N. and Wu, Y. and Kandemir, M.},
year = {2025},
booktitle = {European Conference on Artificial Intelligence},
url = {https://arxiv.org/abs/2402.03055},
}