Model-based reinforcement learning for offline zero-sum Markov games
Year of publication: |
2024
|
---|---|
Authors: | Yan, Yuling ; Li, Gen ; Chen, Yuxin ; Fan, Jianqing |
Published in: |
Operations research. - Linthicum, Md. : INFORMS, ISSN 1526-5463, ZDB-ID 2019440-7. - Vol. 72.2024, 6, p. 2430-2445
|
Subject: | curse of multiple agents | Machine Learning and Data Science | minimax optimality | model-based approach | Nash equilibrium | offline RL | unilateral coverage | zero-sum Markov games | Markov-Kette | Markov chain | Künstliche Intelligenz | Artificial intelligence | Spieltheorie | Game theory | Nash-Gleichgewicht | Lernprozess | Learning process |
-
Learning Markov models via low-rank optimization
Zhu, Ziwei, (2022)
-
Bennett, Andrew, (2024)
-
Kallus, Nathan, (2022)
- More ...
-
Nonparametric function estimation involving errors-in-variables
Fan, Jianqing, (1990)
-
On the estimation of quadratic functions
Fan, Jianqing, (1989)
-
Nonparametric regression with errors in variables
Fan, Jianqing, (1990)
- More ...