Sound Search in Imperfect Information Games

06/15/2020
by   Michal Šustr, et al.
0

Search has played a fundamental role in computer game research since the very beginning. And while online search has been commonly used in perfect information games such as Chess and Go, online search methods for imperfect information games have only been introduced relatively recently. This paper addresses the question of what is sound search in an imperfect information setting of two-player zero-sum games? We argue that the fixed-strategy definitions of exploitability and epsilon-Nash equilibria are ill suited to measure the worst-case performance of an online search algorithm. We thus formalize epsilon-soundness, a concept that connects the worst-case performance of an online algorithm to the performance of an epsilon-Nash equilibrium. As epsilon-soundness can be difficult to compute in general, we also introduce a consistency framework – a hierarchy that connects the behavior of an online algorithm to a Nash equilibrium. Our multiple levels of consistency describe in what sense an online algorithm plays “just like a fixed Nash equilibrium”. These notions further illustrate the difference in perfect and imperfect information settings, as the same consistency guarantees have different worst-case online performance in perfect and imperfect information games. Our definition of soundness and the consistency hierarchy finally provide appropriate tools to analyze online algorithms in imperfect information games. We thus inspect some of the previous online algorithms in a new light, bringing new insights into their worst case performance guarantees.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/26/2020

Computing Nash Equilibria in Multiplayer DAG-Structured Stochastic Games with Persistent Imperfect Information

Many important real-world settings contain multiple players interacting ...
research
03/30/2021

The Price of Anarchy is Fragile in Single-Selection Coverage Games

This paper considers coverage games in which a group of agents are taske...
research
02/19/2020

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

In this paper we investigate the Follow the Regularized Leader dynamics ...
research
03/22/2019

Monte Carlo Neural Fictitious Self-Play: Approach to Approximate Nash equilibrium of Imperfect-Information Games

Researchers on artificial intelligence have achieved human-level intelli...
research
03/10/2016

Bayesian Opponent Exploitation in Imperfect-Information Games

Two fundamental problems in computational game theory are computing a Na...
research
11/10/2021

Search in Imperfect Information Games

From the very dawn of the field, search with value functions was a funda...
research
03/04/2016

Analyzing Games with Ambiguous Player Types using the MINthenMAX Decision Model

In many common interactive scenarios, participants lack information abou...

Please sign up or login with your details

Forgot password? Click here to reset