cs.GTAug 25, 2025

Consistent Opponent Modeling in Imperfect-Information Games

Authors: Sam Ganzfried

Organizations: Ganzfried Research

Abstract

The goal of agents in multi-agent environments is to maximize total reward against the opposing agents that are encountered. Following a game-theoretic solution concept, such as Nash equilibrium, may obtain a strong performance in some settings; however, such approaches fail to capitalize on historical and observed data from repeated interactions against our opponents. Opponent modeling algorithms integrate machine learning techniques to exploit suboptimal opponents utilizing available data; however, the effectiveness of such approaches in imperfect-information games to date is quite limited. We show that existing opponent modeling approaches fail to satisfy a simple desirable property even against static opponents drawn from a known prior distribution; namely, they do not guarantee that the model approaches the opponent's true strategy even in the limit as the number of iterations approaches infinity. We develop a new algorithm that achieves this property given sufficiently informative observations and runs efficiently by solving a convex minimization problem based on the sequence-form game representation.

Figures & tables

Explore similar work

CardsList
  1. NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games

    Sep 1, 2026Tomáš Holeček, Viliam LisýImperfect-Information GamesZero-Sum Games

  2. Generalized Intention Modeling in Multi-Agent Reinforcement Learning

    May 29, 2026Mateusz Odrowaz-Sypniewski, Jasmine Bayrooti, Ajay Shankar +1Opponent ModelingMulti-Agent Reasoning

  3. When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability

    Oct 13, 2026Marcel Petran, Stefan EdelkampOpponent ModelingMulti-Agent Reinforcement Learning