The apparent conflict between estimation and control - a survey of the two-armed bandit problem

DOI10.1016/0016-0032(76)90138-1MaRDI QIDQ1226072zbMATH OpenOpenAlexFDO

Authors Ian H. Witten

Publication date 1976

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0016-0032(76)90138-1

Mathematics Subject Classification ID

Hamilton-Jacobi theories (49L99) Pattern recognition, speech recognition (68T10) Decision theory for games (91A35) Probabilistic games; gambling (91A60) System identification (93B30) Estimation and detection in stochastic control theory (93E10) Optimal stochastic control (93E20)

Cites work

• A note on the two-armed bandit problem with finite memory
• A SEQUENTIAL DECISION PROBLEM WITH A FINITE MEMORY
• A Sequential Design for the Two Armed Bandit
• A study of the relationship between identification and optimization in adaptive control problems
• Contributions to the "Two-Armed Bandit" Problem
• Dual control theory. II
• Finite-memory hypothesis testing--A critique (Corresp.)
• Finite-memory hypothesis testing--Comments on a critique (Corresp.)
• Finite-Time Performance of Some Two-Armed Bandit Controllers
• scientific article; zbMATH DE number 3125136 (Why is no real title available?)
• scientific article; zbMATH DE number 3152611 (Why is no real title available?)
• scientific article; zbMATH DE number 3168214 (Why is no real title available?)
• scientific article; zbMATH DE number 3045589 (Why is no real title available?)
• scientific article; zbMATH DE number 3059214 (Why is no real title available?)
• scientific article; zbMATH DE number 3109895 (Why is no real title available?)
• Hypothesis testing with finite memory in finite time (Corresp.)
• Hypothesis Testing with Finite Statistics
• Learning Automata - A Survey
• Learning with Finite Memory
• On a Problem of Robbins
• On Memory Saved by Randomization
• On Sequential Designs for Maximizing the Sum of n Observations
• On the Asymptotic Performances of Finite-State Two-Armed Bandit Controllers
• On the Theory of Apportionment
• Randomized Rules for the Two-Armed-Bandit with Finite Memory
• Reply to 'Finite memory hypothesis testing - Comments on a critique' by Cover, T.M., and Hellman, M.E.
• Some aspects of the sequential design of experiments
• Testing a simple symmetric hypothesis by a finite-memory deterministic algorithm
• The effects of randomization on finite-memory decision schemes
• The Robbins-Isbell Two-Armed-Bandit Problem with Finite Memory
• The two-armed-bandit problem with time-invariant finite memory

Cited in

(6)

• The N-armed bandit with unimodal structure
• On a general class of absorbing-barrier learning algorithms
• epsilon-optimality of a general class of learning algorithms
• Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function
• Opportunistic spectrum access in unslotted primary systems
• Multiple objective optimization approach to adaptive and learning control

This page was built for publication: The apparent conflict between estimation and control - a survey of the two-armed bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1226072)