Solving Partially Observable Stochastic Games with Public Observations
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00329800" target="_blank" >RIV/68407700:21230/19:00329800 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1609/aaai.v33i01.33012029" target="_blank" >http://dx.doi.org/10.1609/aaai.v33i01.33012029</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1609/aaai.v33i01.33012029" target="_blank" >10.1609/aaai.v33i01.33012029</a>
Alternative languages
Result language
angličtina
Original language name
Solving Partially Observable Stochastic Games with Public Observations
Original language description
n many real-world problems, there is a dynamic interactionbetween competitive agents. Partially observable stochasticgames (POSGs) are among the most general formal mod-els that capture such dynamic scenarios. The model capturesstochastic events, partial information of players about the en-vironment, and the scenario does not have a fixed horizon.Solving POSGs in the most general setting is intractable.Therefore, the research has been focused on subclasses ofPOSGs that have a value of the game and admit designing(approximate) optimal algorithms. We propose such a sub-class for two-player zero-sum games with discounted-sumobjective function—POSGs withpublic observations(PO-POSGs)—where each player is able to reconstruct beliefs ofthe other player over the unobserved states. Our results in-clude: (1) theoretical analysis of PO-POSGs and their valuefunctions showing convexity (concavity) in beliefs of maxi-mizing (minimizing) player, (2) a novel algorithm for approx-imating the value of the game, and (3) a practical demon-stration of scalability of our algorithm. Experimental resultsshow that our algorithm can closely approximate the value ofnon-trivial games with hundreds of states
Czech name
—
Czech description
—
Classification
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)
Result continuities
Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence
ISBN
978-1-57735-809-1
ISSN
2159-5399
e-ISSN
—
Number of pages
8
Pages from-to
2029-2036
Publisher name
AAAI Press
Place of publication
Menlo Park, California
Event location
Honolulu
Event date
Jan 27, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000485292602006