[BibTeX] [RIS]
Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning
Publicatietype: In proceedings
Citatie: Nguyen2026ICAPS
Publication status: Published
Boektitel: Proceedings of the 36th International Conference on Automated Planning and Scheduling (ICAPS)
Deel: 36
Nummer: 1
Jaar: 2026
Maand: Juni
Pagina's: 404--408
Uitgever: AAAI Press
Locatie: Dublin, Ireland
ISSN: 2334-0835
URL: https://ojs.aaai.org/index.php...
DOI: 10.1609/icaps.v36i1.42854
Samenvatting: 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.
Trefwoorden: Boltzmann exploration, decentralized planning, Monte Carlo tree search, multi-agent planning
Auteurs Nguyen, Nhat
Nguyen, Duong
Rizzo, Gianluca
Nguyen, Hung
Toegevoegd door: []
Totaalscore: 0
Bestanden
  • Nguyen2026_ICAPS_Boltzmann_Exp...
Aantekeningen
    Onderwerpen