Reinforcement learning for Golog programs with first-order state-abstraction

DOI10.1093/JIGPAL/JZS011MaRDI QIDQ3165889zbMATH OpenOpenAlexFDO

Authors Daniel Beck, Gerhard Lakemeyer

Publication date 19 October 2012

Published in Logic Journal of the IGPL (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/dd3a840199262686bde37b899fbda1ae3e6d7b97

zbMATH Keywords

Gologreinforcement learningsituation calculus

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Logic in artificial intelligence (68T27) Agent technology and artificial intelligence (68T42)

Recommendations

• Program synthesis using deduction-guided reinforcement learning
• Partially observable game-theoretic agent programming in Golog
• Learning higher-order logic programs
• scientific article; zbMATH DE number 5558275

Cited in

(2)

• Qualitative spatial abstraction in reinforcement learning. Foreword by Christian Freksa.
• Representing value functions with recurrent binary decision diagrams

Describes a project that uses

Uses Software

• GOLOG

This page was built for publication: Reinforcement learning for Golog programs with first-order state-abstraction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3165889)