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.
@article{arxiv.2603.02154,
title = {Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning (Extended Version)},
author = {Nhat D. A. Nguyen and Duong D. Nguyen and Gianluca Rizzo and Hung X. Nguyen},
journal= {arXiv preprint arXiv:2603.02154},
year = {2026}
}