Multi-armed bandit problem revisited

DOI10.1007/BF02191765zbMath0816.90133MaRDI QIDQ1337211

T. Ishikida, Pravin P. Varaiya

Publication date: 13 July 1995

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

zbMATH Keywords

multi-armed bandit problemsuperprocessesdiscounted rewardarm-acquiring banditsoptimality of the Gittins index rule

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items (10)

Optimal unrestricted dynamic stochastic scheduling with partial losses of work due to breakdowns ⋮ Open Bandit Processes with Uncountable States and Time-Backward Effects ⋮ Four proofs of Gittins' multiarmed bandit theorem ⋮ Optimal activation of halting multi‐armed bandit models ⋮ A perpetual search for talents across overlapping generations: a learning process ⋮ An asymptotically optimal policy for finite support models in the multiarmed bandit problem ⋮ MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT ⋮ Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems ⋮ Scheduling Jobs That Are Subject to Deterministic Due Dates and Have Deteriorating Expected Rewards ⋮ A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches

Cites Work

• Unnamed Item
• Unnamed Item
• Continuous multi-armed bandits and multiparameter processes
• Arm-acquiring bandits
• On the Gittins index for multiarmed bandits
• Discrete multiarmed bandits and multiparameter processes
• Optimal strategies for families of alternative bandit processes
• Extensions of the multiarmed bandit problem: The discounted case
• Turnpike Optimality of Smith's Rule in Parallel Machines Stochastic Scheduling

This page was built for publication: Multi-armed bandit problem revisited