Optimal activation of halting multi‐armed bandit models

DOI10.1002/nav.22145arXiv2304.10302MaRDI QIDQ6057028

Michael N. Katehakis, Wesley Cowan, Sheldon M. Ross

Publication date: 25 October 2023

Published in: Naval Research Logistics (NRL) (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2304.10302

zbMATH Keywords

adaptive systemsmachine learningMarkovian decision processesautonomous reasoning and learningdynamic data driven systems

Mathematics Subject Classification ID

Operations research and management science (90Bxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
• Continue, quit, restart probability model
• Stochastic scheduling: a short history of index policies and new approaches to index generation for dynamic resource allocation
• A generalized Gittins index for a Markov chain and its recursive calculation
• On the Gittins index for multiarmed bandits
• Dynamic allocation problems in continuous time
• Multi-armed bandit problem revisited
• A stochastic representation theorem with applications to optimization and obstacle problems.
• Selecting jobs for scheduling on a machine subject to failure
• Finite state multi-armed bandit problems: Sensitive-discount, average-reward and average-overtaking optimality
• Multi‐Armed Bandit Allocation Indices
• Optimal stopping of Markov chains and three abstract optimization problems
• Index Policies for Shooting Problems
• A Note on Stochastic Scheduling on a Single Machine Subject to Breakdown and Repair
• Algorithms for Reinforcement Learning
• The Multi-Armed Bandit Problem: Decomposition and Computation
• On Playing Golf with Two Balls
• A Note on Bandits with a Twist
• Introduction to Multi-Armed Bandits
• MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT
• Risk-Sensitive and Risk-Neutral Multiarmed Bandits
• Replacement of periodically inspected equipment. (An optimal optional stopping rule)
• Applications of Martingale System Theorems
• Scheduling

This page was built for publication: Optimal activation of halting multi‐armed bandit models