Is Q-learning minimax optimal? : a tight sample complexity analysis
Year of publication: |
2024
|
---|---|
Authors: | Li, Gen ; Cai, Changxiao ; Chen, Yuxin ; Wei, Yuting ; Chi, Yuejie |
Published in: |
Operations research. - Linthicum, Md. : INFORMS, ISSN 1526-5463, ZDB-ID 2019440-7. - Vol. 72.2024, 1, p. 222-236
|
Subject: | effective horizon | lower bound | Machine Learning and Data Science | minimax optimality | overestimation | Q-learning | sample complexity | temporal difference learning | Künstliche Intelligenz | Artificial intelligence | Theorie | Theory | Stichprobenerhebung | Sampling | Lernprozess | Learning process | Mathematische Optimierung | Mathematical programming |
-
Breaking the sample size barrier in model-based reinforcement learning with a generative model
Li, Gen, (2024)
-
Learning Markov models via low-rank optimization
Zhu, Ziwei, (2022)
-
Distributionally robust losses for latent covariate mixtures
Duchi, John C., (2023)
- More ...
-
Breaking the sample size barrier in model-based reinforcement learning with a generative model
Li, Gen, (2024)
-
Fast global convergence of natural policy gradient methods with entropy regularization
Cen, Shicong, (2022)
-
Nonconvex low-rank tensor completion from noisy data
Cai, Changxiao, (2022)
- More ...