1. IDR@IIT Indore
  2. IITI Scholarly Publications
  3. Department of Mathematics
Please use this identifier to cite or link to this item: https://dspace.iiti.ac.in/handle/123456789/16976
Full metadata record
DC FieldValueLanguage
dc.contributor.authorShreyas, Sumithra Rudresha R.en_US
dc.contributor.authorVijesh, Antony V.en_US
dc.date.accessioned2025-10-23T12:41:59Z-
dc.date.available2025-10-23T12:41:59Z-
dc.date.issued2025-
dc.identifier.citationShreyas, S. R. R., & Vijesh, A. v. (2025). A multi-step minimax Q-learning algorithm for two-player zero-sum Markov games. Neurocomputing, 657. https://doi.org/10.1016/j.neucom.2025.131552en_US
dc.identifier.issn18728286-
dc.identifier.issn09252312-
dc.identifier.otherEID(2-s2.0-105016786440)-
dc.identifier.urihttps://dx.doi.org/10.1016/j.neucom.2025.131552-
dc.identifier.urihttps://dspace.iiti.ac.in:8080/jspui/handle/123456789/16976-
dc.description.abstractAn interesting iterative procedure is proposed to solve two-player zero-sum Markov games. Under suitable assumptions, the boundedness of the proposed iterates is obtained theoretically. Using results from stochastic approximation, the almost sure convergence of the proposed multi-step minimax Q-learning is obtained theoretically. More specifically, the proposed algorithm converges to the game theoretic optimal value with probability one, when the model information is not known. Numerical simulations authenticate that the proposed algorithm is effective and easy to implement. © 2025 Elsevier B.V., All rights reserved.en_US
dc.language.isoenen_US
dc.publisherElsevier B.V.en_US
dc.sourceNeurocomputingen_US
dc.subjectMinimax Q-learningen_US
dc.subjectMulti-agent Reinforcement Learningen_US
dc.subjectTwo-player Zero-sum Markov Gamesen_US
dc.subjectApproximation Theoryen_US
dc.subjectGame Theoryen_US
dc.subjectIterative Methodsen_US
dc.subjectLearning Algorithmsen_US
dc.subjectMulti Agent Systemsen_US
dc.subjectAlmost Sure Convergenceen_US
dc.subjectBoundednessen_US
dc.subjectMarkov Gamesen_US
dc.subjectMinimax-q Learningen_US
dc.subjectMulti-agent Reinforcement Learningen_US
dc.subjectMultistepsen_US
dc.subjectQ-learning Algorithmsen_US
dc.subjectStochastic Approximationsen_US
dc.subjectTwo-player Zero-sum Markov Gameen_US
dc.subjectZero Sumsen_US
dc.subjectStochastic Systemsen_US
dc.subjectAlgorithmen_US
dc.subjectArticleen_US
dc.subjectControlled Studyen_US
dc.subjectGameen_US
dc.subjectHumanen_US
dc.subjectHuman Experimenten_US
dc.subjectProbabilityen_US
dc.subjectQ Learningen_US
dc.subjectSimulationen_US
dc.titleA multi-step minimax Q-learning algorithm for two-player zero-sum Markov gamesen_US
dc.typeJournal Articleen_US
Appears in Collections:Department of Mathematics

Files in This Item:
There are no files associated with this item.
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetric Badge: