PIMAEX: Multi-Agent Exploration through Peer Incentivization
Kölle, Michael, Tochtermann, Johannes, Schönberger, Julian, Stenzel, Gerhard, Altmann, Philipp, Linnhoff-Popien, Claudia
–arXiv.org Artificial Intelligence
While exploration in single-agent reinforcement learning has been studied extensively in recent years, considerably 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 \textit{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 \textit{PIMAEX} reward in conjunction with \textit{PIMAEX-Communication}, a multi-agent training algorithm that employs a communication channel for agents to influence one another. The evaluation is conducted in the \textit{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 \textit{PIMAEX} reward with \textit{PIMAEX-Communication} outperform those that do not.
arXiv.org Artificial Intelligence
Jan-2-2025
- Country:
- North America > United States
- Massachusetts > Middlesex County > Cambridge (0.04)
- Europe > Germany
- Bavaria > Upper Bavaria > Munich (0.04)
- North America > United States
- Genre:
- Research Report (0.50)
- Technology: