INDEXABILITY AND OPTIMAL INDEX POLICIES FOR A CLASS OF REINITIALISING RESTLESS BANDITS

DOI10.1017/S026996481500025XzbMath1370.90287WikidataQ41925071 ScholiaQ41925071MaRDI QIDQ5358065

Sofía S. Villar

Publication date: 19 September 2017

Published in: Probability in the Engineering and Informational Sciences (Search for Journal in Brave)

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Applications of renewal theory (reliability, demand theory, etc.) (60K10)

Related Items (1)

Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems

Cites Work

• Dynamic priority allocation via restless bandit marginal productivity indices
• Restless bandits, partial conservation laws and indexability
• The Complexity of Optimal Queuing Network Control
• On an index policy for restless bandits
• Computationally Feasible Bounds for Partially Observed Markov Decision Processes
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• Monotone Policies and Indexability for Bidirectional Restless Bandits
• Optimality of Myopic Sensing in Multichannel Opportunistic Access
• Indexability of Restless Bandit Problems and Optimality of Whittle Index for Dynamic Multichannel Access
• Some indexable families of restless bandit problems
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: INDEXABILITY AND OPTIMAL INDEX POLICIES FOR A CLASS OF REINITIALISING RESTLESS BANDITS