A General Upper Bound for the Runtime of a Coevolutionary Algorithm on Impartial Combinatorial Games

TL;DR

This paper establishes a general upper bound on the runtime of coevolutionary algorithms, specifically UMDA, for finding optimal strategies in impartial combinatorial games, advancing theoretical understanding of their efficiency.

Contribution

It provides the first runtime analysis for CoEAs on combinatorial games, deriving a universal upper bound applicable to various game types.

Findings

The upper bound is polynomial or quasipolynomial for many games.

The analysis applies to well-known games like Nim, Chomp, Silver Dollar, and Turning Turtles.

This work advances the theoretical framework for coevolution in game playing.

Abstract

Due to their complex dynamics, combinatorial games are a key test case and application for algorithms that train game playing agents. Among those algorithms that train using self-play are coevolutionary algorithms (CoEAs). However, the successful application of CoEAs for game playing is difficult due to pathological behaviours such as cycling, an issue especially critical for games with intransitive payoff landscapes. Insight into how to design CoEAs to avoid such behaviours can be provided by runtime analysis. In this paper, we push the scope of runtime analysis for CoEAs to combinatorial games, proving a general upper bound for the number of simulated games needed for UMDA to discover (with high probability) an optimal strategy. This result applies to any impartial combinatorial game, and for many games the implied bound is polynomial or quasipolynomial as a function of the number of game positions. After proving the main result, we provide several applications to simple well-known games: Nim, Chomp, Silver Dollar, and Turning Turtles. As the first runtime analysis for CoEAs on combinatorial games, this result is a critical step towards a comprehensive theoretical framework for coevolution.