Shielding in Resource-Constrained Goal POMDPs

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F23%3A00131270" target="_blank" >RIV/00216224:14330/23:00131270 - isvavai.cz</a>
Result on the web
<a href="https://ojs.aaai.org/index.php/AAAI/article/view/26715" target="_blank" >https://ojs.aaai.org/index.php/AAAI/article/view/26715</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1609/aaai.v37i12.26715" target="_blank" >10.1609/aaai.v37i12.26715</a>

Result language
angličtina
Original language name
Shielding in Resource-Constrained Goal POMDPs
Original language description
We consider partially observable Markov decision processes (POMDPs) modeling an agent that needs a supply of a certain resource (e.g., electricity stored in batteries) to operate correctly. The resource is consumed by the agent's actions and can be replenished only in certain states. The agent aims to minimize the expected cost of reaching some goal while preventing resource exhaustion, a problem we call resource-constrained goal optimization (RSGO). We take a two-step approach to the RSGO problem. First, using formal methods techniques, we design an algorithm computing a shield for a given scenario: a procedure that observes the agent and prevents it from using actions that might eventually lead to resource exhaustion. Second, we augment the POMCP heuristic search algorithm for POMDP planning with our shields to obtain an algorithm solving the RSGO problem. We implement our algorithm and present experiments showing its applicability to benchmarks from the literature.
Czech name
—
Czech description
—

Project
<a href="/en/project/GA21-24711S" target="_blank" >GA21-24711S: Efficient Analysis and Optimization for Probabilistic Systems and Games</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 37th AAAI Conference on Artificial Intelligence
ISBN
9781577358800
ISSN
2159-5399
e-ISSN
2374-3468
Number of pages
9
Pages from-to
14674-14682
Publisher name
AAAI Press
Place of publication
Washington, DC, USA
Event location
Washington, DC, USA
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)