Solving Partially Observable Stochastic Shortest-Path Games

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

Solving Partially Observable Stochastic Shortest-Path Games

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

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

Publication year

2021

Confidentiality

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

Article name in the collection

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

ISBN

978-0-9992411-9-6

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

4182-4189

Publisher name

International Joint Conferences on Artificial Intelligence Organization

Place of publication

—

Event location

Montreal

Event date

Aug 19, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—