Evaluating policies for generalized bandits via a notion of duality
From MaRDI portal
Publication:4519117
DOI10.1239/JAP/1014842557zbMath1015.90083OpenAlexW2058616389MaRDI QIDQ4519117
J. H. Crosbie, K. D. Glazenbrook
Publication date: 10 July 2003
Published in: Journal of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1239/jap/1014842557
Stochastic scheduling theory in operations research (90B36) Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40)
This page was built for publication: Evaluating policies for generalized bandits via a notion of duality