Imperfect-Recall Abstractions with Bounds in Games

TL;DR

This paper introduces the first general, algorithm-agnostic guarantees for the solution quality of imperfect-recall abstractions in games, providing tighter bounds and a novel clustering-based abstraction algorithm with theoretical assurances.

Contribution

It offers the first general solution quality guarantees for imperfect-recall abstractions, introduces a clustering approach for bound-minimizing abstractions, and analyzes the metric properties of abstraction inputs.

Findings

Tighter bounds can exponentially reduce solution error.

A reduction to clustering enables bound-minimizing abstractions.

The input space's metric properties depend on payoff scaling.

Abstract

Imperfect-recall abstraction has emerged as the leading paradigm for practical large-scale equilibrium computation in incomplete-information games. However, imperfect-recall abstractions are poorly understood, and only weak algorithm-specific guarantees on solution quality are known. In this paper, we show the first general, algorithm-agnostic, solution quality guarantees for Nash equilibria and approximate self-trembling equilibria computed in imperfect-recall abstractions, when implemented in the original (perfect-recall) game. Our results are for a class of games that generalizes the only previously known class of imperfect-recall abstractions where any results had been obtained. Further, our analysis is tighter in two ways, each of which can lead to an exponential reduction in the solution quality error bound. We then show that for extensive-form games that satisfy certain properties, the problem of computing a bound-minimizing abstraction for a single level of the game reduces to a clustering problem, where the increase in our bound is the distance function. This reduction leads to the first imperfect-recall abstraction algorithm with solution quality bounds. We proceed to show a divide in the class of abstraction problems. If payoffs are at the same scale at all information sets considered for abstraction, the input forms a metric space. Conversely, if this condition is not satisfied, we show that the input does not form a metric space. Finally, we use these results to experimentally investigate the quality of our bound for single-level abstraction.