A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems
From MaRDI portal
Publication:949395
DOI10.1007/s12351-008-0007-5zbMath1183.90458OpenAlexW2090665572MaRDI QIDQ949395
A. Xanthopoulos, D. E. Koulouriotis
Publication date: 21 October 2008
Published in: Operational Research. An International Journal (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s12351-008-0007-5
Approximation methods and heuristics in mathematical programming (90C59) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Algorithms for evaluating the dynamic allocation index
- Multi-armed bandits in discrete and continuous time
- Dynamic pricing on the internet: Theory and simulations
- Optimal learning and experimentation in bandit problems.
- Extensions of the multiarmed bandit problem: The discounted case
- Switching Costs and the Gittins Index
This page was built for publication: A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems