Fast global convergence of natural policy gradient methods with entropy regularization
Year of publication: |
2022
|
---|---|
Authors: | Cen, Shicong ; Cheng, Chen ; Chen, Yuxin ; Wei, Yuting ; Chi, Yuejie |
Published in: |
Operations research. - Linthicum, Md. : INFORMS, ISSN 1526-5463, ZDB-ID 2019440-7. - Vol. 70.2022, 4, p. 2563-2578
|
Subject: | entropy regularization | global convergence | Machine Learning and Data Science | natural policy gradient methods | reinforcement learning | Entropie | Entropy | Künstliche Intelligenz | Artificial intelligence | Theorie | Theory |
-
Li, Yongchun, (2024)
-
Nonasymptotic analysis of Monte Carlo tree search
Shah, Devavrat, (2022)
-
A Lyapunov theory for finite-sample guarantees of Markovian stochastic approximation
Chen, Zaiwei, (2024)
- More ...
-
Breaking the sample size barrier in model-based reinforcement learning with a generative model
Li, Gen, (2024)
-
Is Q-learning minimax optimal? : a tight sample complexity analysis
Li, Gen, (2024)
-
Flatness promotes modernity : logo flatness and consumers' perception of brand image
Peng, Luluo, (2024)
- More ...