AAAI 2025technical0 citations
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.
BibTeX
@article{Boggess_2025, title={Explanations for Multi-Agent Reinforcement Learning}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35200}, DOI={10.1609/aaai.v39i28.35200}, abstractNote={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.}, number={28}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Boggess, Kayla}, year={2025}, month={Apr.}, pages={29245-29246} }