AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

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

Sizhe Tang, Zuyuan Zhang, Mahdi Imani, Tian Lan

ICML 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Coordination graphs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use NonZero instead of MAZero for planningMuZero-style multi-agent MCTS · MatGame 8 agents 10 actions, non-linear, 1000 stepsmean score: 615.2 -> 637.2Improved
use NonZero instead of MAZero in the smallest non-linear MatGameMuZero-style multi-agent MCTS · MatGame 2 agents 3 actions, non-linear, 500 stepsmean score: 49.1 -> 49.7No clear effect
use NonZero instead of MAZero in the larger linear MatGameMuZero-style multi-agent MCTS · MatGame 4 agents 5 actions, linear, 1000 stepsmean score: 175.2 -> 186.2Improved
use NonZero instead of MAZero on SMAC mapsMuZero-style multi-agent MCTS · SMAC (3m, so_many_baneling, 2m_vs_1z)win rate: over 96% win rate on all 3 maps; 50% to 70% fewer environment steps than MAZeroImproved
use NonZero instead of baselines on SMACv2MuZero-style multi-agent MCTS · SMACv2 (Protoss, Zerg, Terran 5_vs_5)win rate: nearly doubles win rate vs best baselineImproved
add second-order curvature estimation (vs first-order updates only) (ablation)NonZero · MatGame (6 agents 8 actions linear; 8 agents 10 actions non-linear)mean scoreImproved
add hypernetwork mixing net for initializing theta (ablation)NonZero · MatGame (6 agents 8 actions linear; 8 agents 10 actions non-linear)mean scoreImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy