Reinforcement learning from comparisons: three alternatives are enough, two are not

DOI10.1214/16-AAP1271zbMath1379.60081OpenAlexW2962773167MaRDI QIDQ1688021

Jean-François Laslier, Benoît Laslier

Publication date: 4 January 2018

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.aoap/1509696037

zbMATH Keywords

learningtournamenturn process

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Memory and learning in psychology (91E40) Evolutionary games (91A22)

Related Items (3)

An urn model with random multiple drawing and random addition ⋮ Asymptotic behaviour of the one-dimensional ``rock-paper-scissors cyclic cellular automaton ⋮ Multiple drawing multi-colour urns by stochastic approximation

This page was built for publication: Reinforcement learning from comparisons: three alternatives are enough, two are not