Open Bandit Processes with Uncountable States and Time-Backward Effects
From MaRDI portal
Publication:5299564
DOI10.1239/jap/1371648948zbMath1266.90112OpenAlexW2068818013MaRDI QIDQ5299564
Publication date: 26 June 2013
Published in: Journal of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://projecteuclid.org/euclid.jap/1371648948
Stochastic scheduling theory in operations research (90B36) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40)
Related Items
Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems, Optimal schedule of elective surgery operations subject to disruptions by emergencies, A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches
Cites Work
- Unnamed Item
- Unnamed Item
- A generalized Gittins index for a Markov chain and its recursive calculation
- Arm-acquiring bandits
- On the Gittins index for multiarmed bandits
- A short proof of the Gittins index theorem
- Multi-armed bandit problem revisited
- Index Policies and a Novel Performance Space Structure for a Class of Generalised Branching Bandit Problems
- Multi‐Armed Bandit Allocation Indices
- Branching Bandit Processes
- Extensions of the multiarmed bandit problem: The discounted case
- Open bandit processes and optimal scheduling of queueing networks
- Conservation Laws, Extended Polymatroids and Multiarmed Bandit Problems; A Polyhedral Approach to Indexable Systems
- New results for generalized bandit problems
- Risk-Sensitive and Risk-Neutral Multiarmed Bandits