Complexity and Algorithms for Exploiting Quantal Opponents in Large Two-Player Games
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00351025" target="_blank" >RIV/68407700:21230/21:00351025 - isvavai.cz</a>
Výsledek na webu
<a href="https://ojs.aaai.org/index.php/AAAI/article/view/16701" target="_blank" >https://ojs.aaai.org/index.php/AAAI/article/view/16701</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Complexity and Algorithms for Exploiting Quantal Opponents in Large Two-Player Games
Popis výsledku v původním jazyce
Solution concepts of traditional game theory assume entirely rational players; therefore, their ability to exploit subrational opponents is limited. One type of subrationality that describes human behavior well is the quantal response. While there exist algorithms for computing solutions against quantal opponents, they either do not scale or may provide strategies that are even worse than the entirely-rational Nash strategies. This paper aims to analyze and propose scalable algorithms for computing effective and robust strategies against a quantal opponent in normal-form and extensive-form games. Our contributions are: (1) we define two different solution concepts related to exploiting quantal opponents and analyze their properties; (2) we prove that computing these solutions is computationally hard;(3) therefore, we evaluate several heuristic approximations based on scalable counterfactual regret minimization (CFR); and (4) we identify a CFR variant that exploits the bounded opponents better than the previously used variants while being less exploitable by the worst-case perfectly-rational opponent.
Název v anglickém jazyce
Complexity and Algorithms for Exploiting Quantal Opponents in Large Two-Player Games
Popis výsledku anglicky
Solution concepts of traditional game theory assume entirely rational players; therefore, their ability to exploit subrational opponents is limited. One type of subrationality that describes human behavior well is the quantal response. While there exist algorithms for computing solutions against quantal opponents, they either do not scale or may provide strategies that are even worse than the entirely-rational Nash strategies. This paper aims to analyze and propose scalable algorithms for computing effective and robust strategies against a quantal opponent in normal-form and extensive-form games. Our contributions are: (1) we define two different solution concepts related to exploiting quantal opponents and analyze their properties; (2) we prove that computing these solutions is computationally hard;(3) therefore, we evaluate several heuristic approximations based on scalable counterfactual regret minimization (CFR); and (4) we identify a CFR variant that exploits the bounded opponents better than the previously used variants while being less exploitable by the worst-case perfectly-rational opponent.
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
<a href="/cs/project/GJ18-27483Y" target="_blank" >GJ18-27483Y: Online metody pro řešení her s neúplnou informací</a><br>
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2021
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence
ISBN
978-1-57735-866-4
ISSN
—
e-ISSN
2374-3468
Počet stran výsledku
9
Strana od-do
5575-5583
Název nakladatele
Association for the Advancement of Artificial Intelligence (AAAI)
Místo vydání
Palo Alto, California
Místo konání akce
Virtual Conference
Datum konání akce
2. 2. 2021
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
000680423505079