The Continuum-Armed Bandit Problem
From MaRDI portal
Publication:4862444
DOI10.1137/S0363012992237273zbMath0848.93069MaRDI QIDQ4862444
Publication date: 8 February 1996
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
62G20: Asymptotic properties of nonparametric inference
93E35: Stochastic learning and adaptive control
62L05: Sequential statistical design
Related Items
An asymptotically optimal policy for finite support models in the multiarmed bandit problem, Online linear optimization and adaptive routing