NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Sizhe, Zhang, Zuyuan, Imani, Mahdi, Lan, Tian
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914524863397888
author Tang, Sizhe
Zhang, Zuyuan
Imani, Mahdi
Lan, Tian
author_facet Tang, Sizhe
Zhang, Zuyuan
Imani, Mahdi
Lan, Tian
contents Monte Carlo Tree Search (MCTS) scales poorly in cooperative multi-agent domains because expansion must consider an exponentially large set of joint actions, severely limiting exploration under realistic search budgets. We propose NonZero, which keeps multi-agent MCTS tractable by running surrogate-guided selection over a low-dimensional nonlinear representation using an interaction-guided proposal rule, instead of directly exploring the full joint-action space. Our exploration uses an interaction score: single-agent deviations are ranked by predicted gain, while two-agent deviations are scored by a mixed-difference measure that reveals coordination benefits even when no single agent can improve alone. We formalize candidate proposal as a bandit problem over local deviations and derive a proposal rule, NonZero, with a sublinear local-regret guarantee for reaching approximate graph-local optima without enumerating the joint-action space. Empirically, NonZero improves sample efficiency and final performance on MatGame, SMAC, and SMACv2 relative to strong model-based and model-free baselines under matched search budgets.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00751
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
Tang, Sizhe
Zhang, Zuyuan
Imani, Mahdi
Lan, Tian
Machine Learning
Monte Carlo Tree Search (MCTS) scales poorly in cooperative multi-agent domains because expansion must consider an exponentially large set of joint actions, severely limiting exploration under realistic search budgets. We propose NonZero, which keeps multi-agent MCTS tractable by running surrogate-guided selection over a low-dimensional nonlinear representation using an interaction-guided proposal rule, instead of directly exploring the full joint-action space. Our exploration uses an interaction score: single-agent deviations are ranked by predicted gain, while two-agent deviations are scored by a mixed-difference measure that reveals coordination benefits even when no single agent can improve alone. We formalize candidate proposal as a bandit problem over local deviations and derive a proposal rule, NonZero, with a sublinear local-regret guarantee for reaching approximate graph-local optima without enumerating the joint-action space. Empirically, NonZero improves sample efficiency and final performance on MatGame, SMAC, and SMACv2 relative to strong model-based and model-free baselines under matched search budgets.
title NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
topic Machine Learning
url https://arxiv.org/abs/2605.00751