An asymptotically optimal strategy for constrained multi-armed bandit problems
Year of publication: |
2020
|
---|---|
Authors: | Chang, Hyeong Soo |
Published in: |
Mathematical methods of operations research : ZOR. - Berlin : Springer, ISSN 1432-5217, ZDB-ID 1459420-1. - Vol. 91.2020, 3, p. 545-557
|
Subject: | Multi-armed bandit | Constrained stochastic optimization | Simulation optimization | Constrained Markov decision process | Theorie | Theory | Mathematische Optimierung | Mathematical programming | Simulation | Markov-Kette | Markov chain | Stochastischer Prozess | Stochastic process | Entscheidung | Decision |
-
Faster algorithm and sharper analysis for constrained Markov decision process
Li, Tianjiao, (2024)
-
Condition-based production for stochastically deteriorating systems : optimal policies and learning
Drent, Collin, (2024)
-
Augmented Markov chain Monte Carlo simulation for two-stage stochastic programs with recourse
Ekin, Tahir, (2014)
- More ...
-
Simulation-based algorithms for Markov decision processes
Fu, Michael, (2007)
-
Multi-policy iteration with a distributed voting
Chang, Hyeong Soo, (2004)
-
Multi-policy iteration with a distributed voting
Chang, Hyeong Soo, (2004)
- More ...