A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches

DOI10.1137/19M1282386zbMath1483.90092arXiv1808.06314MaRDI QIDQ5020738

Xianyi Wu, Wenqing Bao, Xiaoqiang Cai

Publication date: 7 January 2022

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.06314

zbMATH Keywords

Gittins indexstochastic adaptive controlmultiarmed bandit processesmachine learning/reinforcement learningrestricted stopping time

Mathematics Subject Classification ID

Stochastic programming (90C15) Markov and semi-Markov decision processes (90C40)

Related Items

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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Gittins indices in the dynamic allocation problem for diffusion processes
• Continuous multi-armed bandits and multiparameter processes
• Arm-acquiring bandits
• Multi-armed bandits in discrete and continuous time
• Discrete multiarmed bandits and multiparameter processes
• Dynamic allocation problems in continuous time
• Multi-armed bandit problem revisited
• Optimal stopping problems with restricted stopping times
• Optimal stochastic scheduling
• Consistency of Sequential Bayesian Sampling Policies
• Multi‐Armed Bandit Allocation Indices
• Stochastic Scheduling Subject to Preemptive-Repeat Breakdowns with Incomplete Information
• On the Optimal Reward Function of the Continuous Time Multiarmed Bandit Problem
• Branching Bandit Processes
• Index policies for discounted bandit problems with availability constraints
• Extensions of the multiarmed bandit problem: The discounted case
• A Survey of Some Results in Stochastic Adaptive Control
• Continuous-time allocation indices and their discrete-time approximation
• Switching Costs and the Gittins Index
• Restless Bandits, Linear Programming Relaxations, and a Primal-Dual Index Heuristic
• General Gittins index processes in discrete time.
• The Continuum-Armed Bandit Problem
• Open Bandit Processes with Uncountable States and Time-Backward Effects
• MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT
• ASYMPTOTICALLY OPTIMAL MULTI-ARMED BANDIT POLICIES UNDER A COST CONSTRAINT
• Applications of Martingale System Theorems