Answer-set-programming-based abstractions for reinforcement learning

DOI10.1017/S1471068426100544MaRDI QIDQ7406145zbMATH OpenFDO

Authors Rafael Bankosegger, Thomas Eiter, Johannes Oetsch

Publication date 2026

Published in Theory and Practice of Logic Programming (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1017/S1471068426100544

zbMATH Keywords

ASPrelational reinforcement learningstate-action-space abstractions

Mathematics Subject Classification ID

Logic programming (68N17)

Cites work

• \({\mathcal Q}\)-learning
• Abstraction for non-ground answer set programs
• ASP-Core-2 input language format
• Blocks World revisited
• Bridging the gap between reinforcement learning and knowledge representation: a logical off- and on-policy framework
• Detect, understand, act: a neuro-symbolic hierarchical reinforcement learning framework
• Foundations of inductive logic programming
• Inductive Logic Programming
• Reinforcement learning. An introduction
• The logic of adaptive behavior. Knowledge representation and algorithms for adaptive sequential decision making under uncertainty in first-order and relational domains.

This page was built for publication: Answer-set-programming-based abstractions for reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7406145)