PIMAEX: Multi-Agent Exploration through Peer Incentivization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916548322525184 |
|---|---|
| author | Kölle, Michael Tochtermann, Johannes Schönberger, Julian Stenzel, Gerhard Altmann, Philipp Linnhoff-Popien, Claudia |
| author_facet | Kölle, Michael Tochtermann, Johannes Schönberger, Julian Stenzel, Gerhard Altmann, Philipp Linnhoff-Popien, Claudia |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01266 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PIMAEX: Multi-Agent Exploration through Peer Incentivization Kölle, Michael Tochtermann, Johannes Schönberger, Julian Stenzel, Gerhard Altmann, Philipp Linnhoff-Popien, Claudia Multiagent Systems 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. |
| title | PIMAEX: Multi-Agent Exploration through Peer Incentivization |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2501.01266 |