arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2603.02154cs.MAcs.AI
收藏

基于玻尔兹曼的探索用于鲁棒的去中心化多智能体规划(扩展版)

Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning (Extended Version)

Nhat D. A. Nguyen, Duong D. Nguyen, Gianluca Rizzo, Hung X. Nguyen

AI总结:

本文提出CB-MCTS,通过玻尔兹曼策略和熵奖励提升多智能体规划的鲁棒性,在欺骗场景中表现更优。

摘要:

去中心化蒙特卡洛树搜索(Dec-MCTS)被广泛用于协作多智能体规划,但在稀疏或倾斜奖励环境中表现不佳。我们引入了协调玻尔兹曼MCTS(CB-MCTS),它用随机玻尔兹曼策略和衰减熵奖励替代确定性UCT。尽管玻尔兹曼探索已在单智能体MCTS中被研究,但在多智能体系统中应用却面临独特挑战。CB-MCTS是首个解决此问题的。我们分析了CB-MCTS在简单遗憾设置中的表现,并在模拟中展示其在欺骗场景中优于Dec-MCTS,在标准基准上保持竞争力,为多智能体规划提供了一种稳健的解决方案。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑