EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Emergent cooperation from mutual acknowledgment exchange in multi-agent reinforcement learning

Thomy Phan, Felix Sommer, Fabian Ritz, Philipp Altmann, Jonas Nüßlein, Michael Kölle, Lenz Belzner, Claudia Linnhoff-Popien

Autonomous Agents and Multi-Agent Systems · 2024-12 · 38 (2)

DOI: 10.1007/s10458-024-09666-5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Autonomous Agents and Multi-Agent Systems, online erschienen am 11.07.2024. Verfasst von Thomy Phan und 7 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ludwig-Maximilians-Universität München.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Peer incentivization (PI) is a recent approach where all agents learn to reward or penalize each other in a distributed fashion, which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in order to exchange rewards. These rewards are directly incorporated into the learning process without any chance to respond with feedback. Furthermore, most PI approaches rely on global information, which limits scalability and applicability to real-world scenarios where only local information is accessible. In this paper, we propose Mutual Acknowledgment Token Exchange (MATE) , a PI approach defined by a two-phase communication protocol to exchange acknowledgment tokens as incentives to shape individual rewards mutually. All agents condition their token transmissions on the locally estimated quality of their own situations based on environmental rewards and received tokens. MATE is completely decentralized and only requires local communication and information. We evaluate MATE in three social dilemma domains. Our results show that MATE is able to achieve and maintain significantly higher levels of cooperation than previous PI approaches. In addition, we evaluate the robustness of MATE in more realistic scenarios, where agents can deviate from the protocol and communication failures can occur. We also evaluate the sensitivity of MATE w.r.t. the choice of token values.

Förderung

  • Ludwig-Maximilians-Universität München

Zitieren

APA

Phan, T., Sommer, F., Ritz, F., Altmann, P., Nüßlein, J., Kölle, M., Belzner, L., & Linnhoff-Popien, C. (2024). Emergent cooperation from mutual acknowledgment exchange in multi-agent reinforcement learning. Autonomous Agents and Multi-Agent Systems, 38(2). https://doi.org/10.1007/s10458-024-09666-5

Vancouver

Phan T, Sommer F, Ritz F, Altmann P, Nüßlein J, Kölle M, et al. Emergent cooperation from mutual acknowledgment exchange in multi-agent reinforcement learning. Autonomous Agents and Multi-Agent Systems. 2024;38(2). doi:10.1007/s10458-024-09666-5

BibTeX
@article{Phan2024,
  author = {Phan, Thomy and Sommer, Felix and Ritz, Fabian and Altmann, Philipp and Nüßlein, Jonas and Kölle, Michael and Belzner, Lenz and Linnhoff-Popien, Claudia},
  title = {Emergent cooperation from mutual acknowledgment exchange in multi-agent reinforcement learning},
  journal = {Autonomous Agents and Multi-Agent Systems},
  year = {2024},
  volume = {38},
  number = {2},
  doi = {10.1007/s10458-024-09666-5}
}
Kostenlos starten →