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

DOI10.1016/0016-0032(76)90138-1zbMath0326.93024OpenAlexW2124402837MaRDI QIDQ1226072

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

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

Related Items (6)

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 ⋮ On a general class of absorbing-barrier learning algorithms ⋮ epsilon-optimality of a general class of learning algorithms ⋮ The N-armed bandit with unimodal structure

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Dual control theory. II
• A study of the relationship between identification and optimization in adaptive control problems
• A SEQUENTIAL DECISION PROBLEM WITH A FINITE MEMORY
• On Sequential Designs for Maximizing the Sum of $n$ Observations
• A Sequential Design for the Two Armed Bandit
• Contributions to the "Two-Armed Bandit" Problem
• On the Asymptotic Performances of Finite-State Two-Armed Bandit Controllers
• Testing a simple symmetric hypothesis by a finite-memory deterministic algorithm
• On the Theory of Apportionment
• Learning Automata - A Survey
• Finite-Time Performance of Some Two-Armed Bandit Controllers
• The Robbins-Isbell Two-Armed-Bandit Problem with Finite Memory
• A note on the two-armed bandit problem with finite memory
• Hypothesis Testing with Finite Statistics
• Randomized Rules for the Two-Armed-Bandit with Finite Memory
• The two-armed-bandit problem with time-invariant finite memory
• Learning with Finite Memory
• Finite-memory hypothesis testing--A critique (Corresp.)
• Finite-memory hypothesis testing--Comments on a critique (Corresp.)
• Reply to 'Finite memory hypothesis testing - Comments on a critique' by Cover, T.M., and Hellman, M.E.
• On Memory Saved by Randomization
• The effects of randomization on finite-memory decision schemes
• Hypothesis testing with finite memory in finite time (Corresp.)
• On a Problem of Robbins
• Some aspects of the sequential design of experiments

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