Faster algorithm and sharper analysis for constrained Markov decision process
Year of publication: |
2024
|
---|---|
Authors: | Li, Tianjiao ; Guan, Ziwei ; Zou, Shaofeng ; Xu, Tengyu ; Liang, Yingbin ; Lan, Guanghui |
Published in: |
Operations research letters : a journal of INFORMS devoted to the rapid publication of concise contributions in operations research. - Amsterdam [u.a.] : Elsevier Science, ISSN 0167-6377, ZDB-ID 1467065-3. - Vol. 54.2024, Art.-No. 107107, p. 1-7
|
Subject: | Accelerated gradient method | Constrained Markov decision process | Entropy regularization | Policy optimization | Primal-dual algorithm | Theorie | Theory | Markov-Kette | Markov chain | Mathematische Optimierung | Mathematical programming | Entscheidung | Decision | Algorithmus | Algorithm | Entropie | Entropy |
-
An asymptotically optimal strategy for constrained multi-armed bandit problems
Chang, Hyeong Soo, (2020)
-
Rank-1 transition uncertainties in constrained Markov decision processes
Varagapriya, V., (2024)
-
A unified algorithm framework for mean-variance optimization in discounted Markov decision processes
Ma, Shuai, (2023)
- More ...
-
A note on inexact gradient and Hessian conditions for cubic regularized Newton’s method
Wang, Zhe, (2019)
-
Shi, Rong, (2022)
-
Does short-term momentum exist in China?
Yue, Tian, (2023)
- More ...