Algebraic results and bottom-up algorithm for policies generalization in reinforcement learning using concept lattices

DOI10.1016/J.NAHS.2006.12.001zbMATH Open1169.68042OpenAlexW2025228809WikidataQ115039494 ScholiaQ115039494MaRDI QIDQ1003553FDOQ1003553

Authors: Marc Ricordeau, Michel Liquière 

Publication date: 4 March 2009

Published in: Nonlinear Analysis. Hybrid Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.nahs.2006.12.001

Recommendations

• Algebraic reinforcement learning. Hypothesis induction for relational reinforcement learning using term generalization.
• Learning generalized policies from planning examples using concept languages
• Towards min max generalization in reinforcement learning
• scientific article; zbMATH DE number 67800
• A generalization error for Q-learning

zbMATH Keywords

reinforcement learningGalois lattices

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Knowledge representation (68T30)

Cites Work

• Title not available (Why is that?)
• \({\mathcal Q}\)-learning
• Title not available (Why is that?)
• Title not available (Why is that?)
• Equivalence notions and model minimization in Markov decision processes
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Relational reinforcement learning

Cited In (4)

• Algebraic reinforcement learning. Hypothesis induction for relational reinforcement learning using term generalization.
• Learning generalized policies from planning examples using concept languages
• A new algebraic structure for formal concept analysis
• Title not available (Why is that?)

This page was built for publication: Algebraic results and bottom-up algorithm for policies generalization in reinforcement learning using concept lattices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1003553)