Discrete multiarmed bandits and multiparameter processes
From MaRDI portal
Publication:1317211
DOI10.1007/BF00366276zbMath0788.60056MaRDI QIDQ1317211
Publication date: 21 April 1994
Published in: Probability Theory and Related Fields (Search for Journal in Brave)
Signal detection and filtering (aspects of stochastic processes) (60G35) Optimal stochastic control (93E20)
Related Items
An optimal stopping zero-sum game in discrete-time multi-armed bandit processes ⋮ A bisection/successive approximation method for computing Gittins indices ⋮ Multi-armed bandit problem revisited ⋮ Four proofs of Gittins' multiarmed bandit theorem ⋮ On an Optimal Stopping Problem for Multi-Parameter Diffusion Processes ⋮ Zero-sum Games for Discrete-time Multi-armed Bandit Processes with a Generalized Discount ⋮ Stochastic control of two-parameter processes application:the two-armed bandit problem ⋮ Triangular function and continuity property of multiparameter optimal stopping value ⋮ Continuity Properties of Optimal Multiple Stopping Value ⋮ Additive comparisons of stopping values and supremum values for finite stage multiparameter stochastic processes ⋮ Lower semicontinuity property of multiparameter optimal stopping value and its application to multiparameter prophet inequalities ⋮ Prophet inequalities for two-parameter optimal stopping problems ⋮ A Fatou equation for a two-parameter stochastic process ⋮ Baxter-Chacon topology and optimality for multivariate stopping of two-parameter stochastic processes ⋮ Prophet inequalities for finite stage multiparameter optimal stopping problems ⋮ Optimal learning with non-Gaussian rewards ⋮ Discrete time multi-parameter optimal stopping problems with multiple plays and switching costs ⋮ Optimal multiple stopping problems for discrete time multiparameter stochastic processes ⋮ Scheduling Jobs That Are Subject to Deterministic Due Dates and Have Deteriorating Expected Rewards ⋮ Gittins' theorem under uncertainty ⋮ Multi-armed bandits in discrete and continuous time ⋮ A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches ⋮ Optimal stopping problems for multiarmed bandit processes with arms' independence
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Gittins indices in the dynamic allocation problem for diffusion processes
- Markov strategies for optimal control problems indexed by a partially ordered set
- Stopping rules and tactics for processes indexed by a directed set
- Optional sampling of submartingales indexed by partially ordered sets
- Stochastic integrals in the plane
- Extensions of the multiarmed bandit problem: The discounted case
- Optimal stopping and supermartingales over partially ordered sets
- [https://portal.mardi4nfdi.de/wiki/Publication:3949750 Arr�t Optimal sur le Plan]
- Applications of Martingale System Theorems
