Multiagent Evaluation under Incomplete Information

TL;DR

This paper develops new methods for accurately evaluating and ranking multiagent strategies in complex, noisy, incomplete information environments, extending existing approaches like Elo and {\

Contribution

It introduces adaptive algorithms with proven guarantees for ranking agents under noisy, incomplete information, addressing limitations of prior methods like Elo and {\

Findings

Proposed algorithms achieve accurate rankings in noisy multiagent settings.

Derived sample complexity bounds for confident ranking.

Validated methods on diverse domains including Bernoulli games and Kuhn poker.

Abstract

This paper investigates the evaluation of learned multiagent strategies in the incomplete information setting, which plays a critical role in ranking and training of agents. Traditionally, researchers have relied on Elo ratings for this purpose, with recent works also using methods based on Nash equilibria. Unfortunately, Elo is unable to handle intransitive agent interactions, and other techniques are restricted to zero-sum, two-player settings or are limited by the fact that the Nash equilibrium is intractable to compute. Recently, a ranking method called {\alpha}-Rank, relying on a new graph-based game-theoretic solution concept, was shown to tractably apply to general games. However, evaluations based on Elo or {\alpha}-Rank typically assume noise-free game outcomes, despite the data often being collected from noisy simulations, making this assumption unrealistic in practice. This paper investigates multiagent evaluation in the incomplete information regime, involving general-sum many-player games with noisy outcomes. We derive sample complexity guarantees required to confidently rank agents in this setting. We propose adaptive algorithms for accurate ranking, provide correctness and sample complexity guarantees, then introduce a means of connecting uncertainties in noisy match outcomes to uncertainties in rankings. We evaluate the performance of these approaches in several domains, including Bernoulli games, a soccer meta-game, and Kuhn poker.