Explanations for Multi-Agent Reinforcement Learning
Abstract
Explainable reinforcement learning (xRL) provides explanations for ``black-box" decision making systems. However, most work in xRL is based on single-agent settings instead of the more complex multi-agent reinforcement learning (MARL). Several different types of post-hoc explanations must be provided to increase understanding of both centralized and decentralized MARL systems. For centralized MARL, this research develops methods to generate global policy summaries, query-based explanations, and temporal explanations. For decentralized MARL, this research develops global policy summaries and query-based explanations.
Cite
Text
Boggess. "Explanations for Multi-Agent Reinforcement Learning." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35200Markdown
[Boggess. "Explanations for Multi-Agent Reinforcement Learning." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/boggess2025aaai-explanations/) doi:10.1609/AAAI.V39I28.35200BibTeX
@inproceedings{boggess2025aaai-explanations,
title = {{Explanations for Multi-Agent Reinforcement Learning}},
author = {Boggess, Kayla},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {29245-29246},
doi = {10.1609/AAAI.V39I28.35200},
url = {https://mlanthology.org/aaai/2025/boggess2025aaai-explanations/}
}