Heuristic Search Value Iteration for One-Sided Partially Observable Stochastic Games

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00315202" target="_blank" >RIV/68407700:21230/17:00315202 - isvavai.cz</a>

Výsledek na webu

<a href="https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14739/13812" target="_blank" >https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14739/13812</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Heuristic Search Value Iteration for One-Sided Partially Observable Stochastic Games

Popis výsledku v původním jazyce

Security problems can be modeled as two-player partially observable stochastic games with one-sided partial observability and infinite horizon (one-sided POSGs). We seek for optimal strategies of player 1 that correspond to robust strategies against the worst-case opponent (player 2) that is assumed to have a perfect information about the game. We present a novel algorithm for approximately solving one-sided POSGs based on the heuristic search value iteration (HSVI) for POMDPs. Our results include (1) theoretical properties of one-sided POSGs and their value functions, (2) guarantees showing the convergence of our algorithm to optimal strategies, and (3) practical demonstration of applicability and scalability of our algorithm on three different domains: pursuit-evasion, patrolling, and search games.

Název v anglickém jazyce

Heuristic Search Value Iteration for One-Sided Partially Observable Stochastic Games

Popis výsledku anglicky

Security problems can be modeled as two-player partially observable stochastic games with one-sided partial observability and infinite horizon (one-sided POSGs). We seek for optimal strategies of player 1 that correspond to robust strategies against the worst-case opponent (player 2) that is assumed to have a perfect information about the game. We present a novel algorithm for approximately solving one-sided POSGs based on the heuristic search value iteration (HSVI) for POMDPs. Our results include (1) theoretical properties of one-sided POSGs and their value functions, (2) guarantees showing the convergence of our algorithm to optimal strategies, and (3) practical demonstration of applicability and scalability of our algorithm on three different domains: pursuit-evasion, patrolling, and search games.

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)

Projekt

<a href="/cs/project/GA15-23235S" target="_blank" >GA15-23235S: Abstrakce a extenzivní hry s nedokonalou pamětí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence

ISBN

978-1-57735-780-3

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

558-564

Název nakladatele

AAAI Press

Místo vydání

Menlo Park

Místo konání akce

San Francisco

Datum konání akce

4. 2. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—