PIMAEX: Multi-Agent Exploration Through Peer Incentivization
Michael Kölle, Johannes Tochtermann, Julian Schönberger, Gerhard Stenzel, Philipp Altmann and Claudia Linnhoff-Popien
Abstract: While exploration in single-agent reinforcement learning has been studied extensively in recent years, consid-erably less work has focused on its counterpart in multi-agent reinforcement learning. To address this issue, this work proposes a peer-incentivized reward function inspired by previous research on intrinsic curiosity and influence-based rewards. The PIMAEX reward, short for Peer-Incentivized Multi-Agent Exploration, aims to improve exploration in the multi-agent setting by encouraging agents to exert influence over each other to increase the likelihood of encountering novel states. We evaluate the PIMAEX reward in conjunction with PIMAEX-Communication, a multi-agent training algorithm that employs a communication channel for agents to influence one another. The evaluation is conducted in the Consume/Explore environment, a partially observable environment with deceptive rewards, specifically designed to challenge the exploration vs. exploitation dilemma and the credit-assignment problem. The results empirically demonstrate that agents using the PI-MAEX reward with PIMAEX-Communication outperform those that do not.
Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, pp. 572-579 (2025)
Cite This Work
Switch between citation styles and copy the format you need.
Citation
Michael Kölle, Johannes Tochtermann, Julian Schönberger, Gerhard Stenzel, Philipp Altmann, and Claudia Linnhoff-Popien. “PIMAEX: Multi-Agent Exploration Through Peer Incentivization.” Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART , pp. 572-579 , 2025. https://doi.org/10.5220/0013260000003890
