Multi-task reinforcement learning in partially observable stochastic environments

MaRDI QIDQ2880921zbMATH OpenFDO

Authors Xuejun Liao, Lawrence Carin, Hui Li

Publication date 17 April 2012

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL http://www.jmlr.org/papers/v10/li09b.html

zbMATH Keywords

Dirichlet processesmulti-task learningpartially observable Markov decision processesregionalized policy representationreinforcement learning

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) Bayesian problems; characterization of Bayes procedures (62C10) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• A Bayesian approach for learning and planning in partially observable Markov decision processes
• Multi-task learning for classification with Dirichlet process priors
• Reinforcement learning of non-Markov decision processes
• Inverse reinforcement learning in partially observable environments
• scientific article; zbMATH DE number 1849154

Cited in

(3)

• Decision Learning and Adaptation Over Multi-Task Networks
• scientific article; zbMATH DE number 2243380 (Why is no real title available?)
• Partially observable collaborative model for optimizing personalized treatment selection

This page was built for publication: Multi-task reinforcement learning in partially observable stochastic environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2880921)