EUVIMEDEUVIMED entdecken
Crossref

Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning

Nhat Nguyen, Duong Nguyen, Gianluca Rizzo, Hung Nguyen

Proceedings of the International Conference on Automated Planning and Scheduling · 08.06.2026 · 36 (1) · 404-408

DOI: 10.1609/icaps.v36i1.42854 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the International Conference on Automated Planning and Scheduling, online erschienen am 08.06.2026. Verfasst von Nhat Nguyen und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Decentralized Monte Carlo Tree Search (Dec-MCTS) is widely used for cooperative multi-agent planning but struggles in sparse or skewed reward environments. We introduce Coordinated Boltzmann MCTS (CB-MCTS), which replaces deterministic UCT with a stochastic Boltzmann policy and a decaying entropy bonus for sustained yet focused exploration. While Boltzmann exploration has been studied in single-agent MCTS, applying it in multi-agent systems poses unique challenges. CB-MCTS is the first to address this. We analyze CB‑MCTS in the simple-regret setting and show in simulations that it outperforms Dec-MCTS in deceptive scenarios and remains competitive on standard benchmarks, providing a robust solution for multi-agent planning.

Zitieren

APA

Nguyen, N., Nguyen, D., Rizzo, G., & Nguyen, H. (2026). Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning. Proceedings of the International Conference on Automated Planning and Scheduling, 36(1), 404-408. https://doi.org/10.1609/icaps.v36i1.42854

Vancouver

Nguyen N, Nguyen D, Rizzo G, Nguyen H. Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning. Proceedings of the International Conference on Automated Planning and Scheduling. 2026;36(1):404-408. doi:10.1609/icaps.v36i1.42854

BibTeX
@article{Nguyen2026,
  author = {Nguyen, Nhat and Nguyen, Duong and Rizzo, Gianluca and Nguyen, Hung},
  title = {Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning},
  journal = {Proceedings of the International Conference on Automated Planning and Scheduling},
  year = {2026},
  volume = {36},
  number = {1},
  pages = {404--408},
  doi = {10.1609/icaps.v36i1.42854}
}
Kostenlos starten →