Please use this identifier to cite or link to this item:
https://dspace.iiti.ac.in/handle/123456789/16976
| Title: | A multi-step minimax Q-learning algorithm for two-player zero-sum Markov games |
| Authors: | Shreyas, Sumithra Rudresha R. Vijesh, Antony V. |
| Keywords: | Minimax Q-learning;Multi-agent Reinforcement Learning;Two-player Zero-sum Markov Games;Approximation Theory;Game Theory;Iterative Methods;Learning Algorithms;Multi Agent Systems;Almost Sure Convergence;Boundedness;Markov Games;Minimax-q Learning;Multi-agent Reinforcement Learning;Multisteps;Q-learning Algorithms;Stochastic Approximations;Two-player Zero-sum Markov Game;Zero Sums;Stochastic Systems;Algorithm;Article;Controlled Study;Game;Human;Human Experiment;Probability;Q Learning;Simulation |
| Issue Date: | 2025 |
| Publisher: | Elsevier B.V. |
| Citation: | Shreyas, 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.2025.131552 |
| Abstract: | An 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. |
| URI: | https://dx.doi.org/10.1016/j.neucom.2025.131552 https://dspace.iiti.ac.in:8080/jspui/handle/123456789/16976 |
| ISSN: | 18728286 09252312 |
| Type of Material: | Journal Article |
| Appears in Collections: | Department of Mathematics |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
Altmetric Badge: