Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games

2026-07-01

AI Summary

This study addresses the challenge of learning effective strategy representations in two-player zero-sum imperfect-information games. To this end, the authors construct a strategy dataset, design a self-supervised embedding method, and evaluate the quality of the learned representations through downstream tasks. Experiments on Kuhn and Leduc poker demonstrate that the proposed approach successfully captures the behavioral and semantic characteristics of strategies. This work is the first to systematically introduce self-supervised learning into the domain of game-theoretic strategy representation, offering a comprehensive framework for strategy embedding learning and evaluation. The results validate the feasibility and potential of this paradigm under fundamental settings.

Abstract

We investigate the problem of learning useful policy representations (embeddings) in two-player zero-sum imperfect-information games. We make three contributions: First, we introduce methods of creating datasets of policies for a given game. Second, we propose methods to learn policy representations. Third, we introduce downstream tasks to evaluate the effectiveness of such representations. We evaluate each dataset method, embedding method, and downstream task on Kuhn and Leduc Poker. Although our methods are very basic, we demonstrate that useful behavioral representations are present in the learned embeddings. To our knowledge, this work is among the first to systematically compare self-supervised learning techniques for learning policy representations in games. Our code is available at https://github.com/VitamintK/ssl-project for others to extend.

Problem

• policy representation
• imperfect-information games
• zero-sum games
• self-supervised learning
• behavioral embeddings

Innovation

• policy representation
• self-supervised learning
• imperfect-information games
• zero-sum games
• behavioral embedding