Shielding in Resource-Constrained Goal POMDPs

Logo poskytovatele

Varování

Publikace nespadá pod Ekonomicko-správní fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

AJDARÓW Michal BRLEJ Šimon NOVOTNÝ Petr

Rok publikování 2023
Druh Článek ve sborníku
Konference Proceedings of the 37th AAAI Conference on Artificial Intelligence
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www https://ojs.aaai.org/index.php/AAAI/article/view/26715
Doi http://dx.doi.org/10.1609/aaai.v37i12.26715
Klíčová slova decision making; Markov decision processes; controller synthesis; resource constraints; shielding
Popis 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.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.