Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning
| Type of publication: | Inproceedings |
| Citation: | Nguyen2026ICAPS |
| Publication status: | Published |
| Booktitle: | Proceedings of the 36th International Conference on Automated Planning and Scheduling (ICAPS) |
| Volume: | 36 |
| Number: | 1 |
| Year: | 2026 |
| Month: | June |
| Pages: | 404--408 |
| Publisher: | AAAI Press |
| Location: | Dublin, Ireland |
| ISSN: | 2334-0835 |
| URL: | https://ojs.aaai.org/index.php... |
| DOI: | 10.1609/icaps.v36i1.42854 |
| Abstract: | 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. |
| Keywords: | Boltzmann exploration, decentralized planning, Monte Carlo tree search, multi-agent planning |
| Authors | |
| Added by: | [] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|
|
Topics
|
|
|
|
|
