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

## Pages

| Page |
| --- |
| [Executive summary](#/executive-summary) |
| [Claim 1: Low-dimensional nonlinear surrogate](#/claim-1-low-dimensional-nonlinear-surrogate) |
| [Claim 2: Regret bound (Theorem 3.5)](#/claim-2-regret-bound-theorem-3-5) |
| [Claim 3: Efficiency separation (Theorem 3.7)](#/claim-3-efficiency-separation-theorem-3-7) |
| [Claim 4: MatGame 8-agent 10-action nonlinear](#/claim-4-matgame-8-agent-10-action-nonlinear) |
| [Claim 5: SMAC win rate](#/claim-5-smac-win-rate) |
| [Claim 6: SMACv2 win rate + ablations](#/claim-6-smacv2-win-rate-ablations) |
| [Conclusion](#/conclusion) |