Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Delage, Aurélien"'
Centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to epsilon-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. This paper
Externí odkaz:
http://arxiv.org/abs/2408.13139
A recent theory shows that a multi-player decentralized partially observable Markov decision process can be transformed into an equivalent single-player game, enabling the application of \citeauthor{bellman}'s principle of optimality to solve the sin
Externí odkaz:
http://arxiv.org/abs/2402.02954
State-of-the-art methods for solving 2-player zero-sum imperfect information games rely on linear programming or regret minimization, though not on dynamic programming (DP) or heuristic search (HS), while the latter are often at the core of state-of-
Externí odkaz:
http://arxiv.org/abs/2210.14640
Dynamic programming and heuristic search are at the core of state-of-the-art solvers for sequential decision-making problems. In partially observable or collaborative settings (\eg, POMDPs and Dec-POMDPs), this requires introducing an appropriate sta
Externí odkaz:
http://arxiv.org/abs/2110.14529
Many non-trivial sequential decision-making problems are efficiently solved by relying on Bellman's optimality principle, i.e., exploiting the fact that sub-problems are nested recursively within the original problem. Here we show how it can apply to
Externí odkaz:
http://arxiv.org/abs/2006.16395
Publikováno v:
Dynamic Games & Applications; Sep2024, Vol. 14 Issue 4, p751-805, 55p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
ROADEF 2022-23ème congrès annuel de la Société Française de Recherche Opérationnelle et d'Aide à la Décision
ROADEF 2022-23ème congrès annuel de la Société Française de Recherche Opérationnelle et d'Aide à la Décision, INSA Lyon, Feb 2022, Villeurbanne-Lyon, France. pp.1-2
ROADEF 2022-23ème congrès annuel de la Société Française de Recherche Opérationnelle et d'Aide à la Décision, INSA Lyon, Feb 2022, Villeurbanne-Lyon, France. pp.1-2
National audience; Max-Min Optimization for Lipschitz-Continuous Functions
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ef3c0070618d307b2c9b613236058316
https://hal.science/hal-03595326/document
https://hal.science/hal-03595326/document
Publikováno v:
JFPDA 2021-Journées Francophones Planification, Décision et Apprentissage
JFPDA 2021-Journées Francophones Planification, Décision et Apprentissage, Jun 2021, Bordeaux (virtuel), France. pp.1-14
JFPDA 2021-Journées Francophones Planification, Décision et Apprentissage, Jun 2021, Bordeaux (virtuel), France. pp.1-14
Solving a 2-player zero-sum partially observable stochastic game (zs-POSG) typically relies on turning it into an extensive-form game, thus losing structural information contained in the original representation. We prevent such a loss by turning the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c403110f24a4701548897faaad9c46e9
https://inria.hal.science/hal-03523951/file/jfpda21.pdf
https://inria.hal.science/hal-03523951/file/jfpda21.pdf
Publikováno v:
JFPDA 2020-Journées Francophones surla Planification, la Décision et l’Apprentissagepour la conduite de systèmes
JFPDA 2020-Journées Francophones surla Planification, la Décision et l’Apprentissagepour la conduite de systèmes, Jun 2020, Angers (virtuel), France. pp.1-3
JFPDA 2020-Journées Francophones surla Planification, la Décision et l’Apprentissagepour la conduite de systèmes, Jun 2020, Angers (virtuel), France. pp.1-3
National audience; Many non-trivial sequential decision-making problems are efficiently solved by relying on Bellman's optimality principle, i.e., exploiting the fact that sub-problems are nested recursively within the original problem. Here we show
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e5bd725096b83aff56287023b7516114
https://hal.inria.fr/hal-03081320
https://hal.inria.fr/hal-03081320