Continual Depth-limited Responses for Computing Counter-strategies in Sequential Games

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Milec, David, Kubíček, Ondřej, Lisý, Viliam
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909157975654400
author Milec, David
Kubíček, Ondřej
Lisý, Viliam
author_facet Milec, David
Kubíček, Ondřej
Lisý, Viliam
contents In zero-sum games, the optimal strategy is well-defined by the Nash equilibrium. However, it is overly conservative when playing against suboptimal opponents and it can not exploit their weaknesses. Limited look-ahead game solving in imperfect-information games allows defeating human experts in massive real-world games such as Poker, Liar's Dice, and Scotland Yard. However, since they approximate Nash equilibrium, they tend to only win slightly against weak opponents. We propose methods combining limited look-ahead solving with an opponent model in order to 1) approximate a best response in large games or 2) compute a robust response with control over the robustness of the response. Both methods can compute the response in real time to previously unseen strategies. We present theoretical guarantees of our methods. We show that existing robust response methods do not work combined with limited look-ahead solving of the shelf, and we propose a novel solution for the issue. Our algorithm performs significantly better than multiple baselines in smaller games and outperforms state-of-the-art methods against SlumBot.
format Preprint
id arxiv_https___arxiv_org_abs_2112_12594
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Continual Depth-limited Responses for Computing Counter-strategies in Sequential Games
Milec, David
Kubíček, Ondřej
Lisý, Viliam
Computer Science and Game Theory
In zero-sum games, the optimal strategy is well-defined by the Nash equilibrium. However, it is overly conservative when playing against suboptimal opponents and it can not exploit their weaknesses. Limited look-ahead game solving in imperfect-information games allows defeating human experts in massive real-world games such as Poker, Liar's Dice, and Scotland Yard. However, since they approximate Nash equilibrium, they tend to only win slightly against weak opponents. We propose methods combining limited look-ahead solving with an opponent model in order to 1) approximate a best response in large games or 2) compute a robust response with control over the robustness of the response. Both methods can compute the response in real time to previously unseen strategies. We present theoretical guarantees of our methods. We show that existing robust response methods do not work combined with limited look-ahead solving of the shelf, and we propose a novel solution for the issue. Our algorithm performs significantly better than multiple baselines in smaller games and outperforms state-of-the-art methods against SlumBot.
title Continual Depth-limited Responses for Computing Counter-strategies in Sequential Games
topic Computer Science and Game Theory
url https://arxiv.org/abs/2112.12594