Solving Partially Observable Stochastic Shortest-Path Games

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00353184" target="_blank" >RIV/68407700:21230/21:00353184 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.24963/ijcai.2021/575" target="_blank" >https://doi.org/10.24963/ijcai.2021/575</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.24963/ijcai.2021/575" target="_blank" >10.24963/ijcai.2021/575</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Solving Partially Observable Stochastic Shortest-Path Games

Popis výsledku v původním jazyce

We study the two-player zero-sum extension of the partially observable stochastic shortest-path problem where one agent has only partial information about the environment. We formulate this problem as a partially observable stochastic game (POSG): given a set of target states and negative rewards for each transition, the player with imperfect information maximizes the expected undiscounted total reward until a target state is reached. The second player with the perfect information aims for the opposite. We base our formalism on POSGs with one-sided observability (OS-POSGs) and give the following contributions: (1) we introduce a novel heuristic search value iteration algorithm that iteratively solves depth-limited variants of the game, (2) we derive the bound on the depth guaranteeing an arbitrary precision, (3) we propose a novel upper-bound estimation that allows early terminations, and (4) we experimentally evaluate the algorithm on a pursuit-evasion game.

Název v anglickém jazyce

Solving Partially Observable Stochastic Shortest-Path Games

Popis výsledku anglicky

We study the two-player zero-sum extension of the partially observable stochastic shortest-path problem where one agent has only partial information about the environment. We formulate this problem as a partially observable stochastic game (POSG): given a set of target states and negative rewards for each transition, the player with imperfect information maximizes the expected undiscounted total reward until a target state is reached. The second player with the perfect information aims for the opposite. We base our formalism on POSGs with one-sided observability (OS-POSGs) and give the following contributions: (1) we introduce a novel heuristic search value iteration algorithm that iteratively solves depth-limited variants of the game, (2) we derive the bound on the depth guaranteeing an arbitrary precision, (3) we propose a novel upper-bound estimation that allows early terminations, and (4) we experimentally evaluate the algorithm on a pursuit-evasion game.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

ISBN

978-0-9992411-9-6

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

4182-4189

Název nakladatele

International Joint Conferences on Artificial Intelligence Organization

Místo vydání

—

Místo konání akce

Montreal

Datum konání akce

19. 8. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—