Approximation Algorithms for Observer Aware MDPs - Department of Complex Systems, Artificial Intelligence  & Robotics
Communication Dans Un Congrès Année : 2024

Approximation Algorithms for Observer Aware MDPs

Résumé

We present approximation algorithms for Observer-Aware Markov Decision Processes (OAMDPs). OAMDPs model sequential decision-making problems in which rewards depend on the beliefs of an observer about the goals, intentions, or capabilities of the observed agent. The first proposed algorithm is a grid-based value iteration (Grid-VI), which discretizes the observer's belief into regular grids. Based on the same discretization, the second proposed algorithm is a variant of Real-Time Dynamic Programming (RTDP) called Grid-RTDP. Unlike Grid-VI, Grid-RTDP focuses its updates on promising states using heuristic estimates. We provide theoretical guarantees of the proposed algorithms and demonstrate that Grid-RTDP has a good anytime performance comparable to the existing approach without performance guarantees.
Fichier principal
Vignette du fichier
302_Approximation_Algorithms_f.pdf (647.78 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04698464 , version 1 (16-09-2024)

Licence

Identifiants

  • HAL Id : hal-04698464 , version 1

Citer

Shuwa Miura, Olivier Buffet, Shlomo Zilberstein. Approximation Algorithms for Observer Aware MDPs. 40th Conference on Uncertainty in Artificial Intelligence (UAI), Negar Kiyavash; Joris Mooij, Jul 2024, Barcelone, Spain. ⟨hal-04698464⟩
0 Consultations
0 Téléchargements

Partager

More