Efficient learning and planning with compressed predictive states

MaRDI QIDQ5249587zbMATH OpenFDO

Authors William Hamilton, Mahdi Milani Fard, Joelle Pineau

Publication date 6 May 2015

Full work available at URL https://arxiv.org/abs/1312.0286, http://jmlr.csail.mit.edu/papers/v15/hamilton14a.html

zbMATH Keywords

dimensionality reductionrandom projectionsreinforcement learningpredictive state representation

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) Multivariate analysis (62H99) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Group sparse optimization for learning predictive state representations
• scientific article; zbMATH DE number 5670432
• scientific article; zbMATH DE number 2243378
• A Bayesian approach for learning and planning in partially observable Markov decision processes
• scientific article; zbMATH DE number 5547961

Cited in

(3)

• Learning to make predictions in partially observable environments without a generative model
• scientific article; zbMATH DE number 7625165 (Why is no real title available?)
• Scalable planning with deep neural network learned transition models

This page was built for publication: Efficient learning and planning with compressed predictive states

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5249587)