Shaping reward signals in reinforcement learning using constraint programming

DOI10.1007/978-3-031-95976-9_16MaRDI QIDQ6897960zbMATH OpenFDO

Authors Chao Yin, Quentin Cappart, Gilles Pesant

Publication date 19 November 2025

Full work available at URL https://doi.org/10.1007/978-3-031-95976-9_16

zbMATH Keywords

AI planningbelief propagationconstraint programmingpotential-based reward shapingreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Applications of mathematical programming (90C90)

Cites work

• A \texttt{cost-regular} based hybrid column generation approach
• Episodic reinforcement learning in finite MDPs: minimax lower bounds revisited
• Exploiting entropy in constraint programming
• From support propagation to belief propagation in constraint programming
• Merge-and-shrink: a compositional theory of transformations of factored transition systems
• Reward machines: exploiting reward function structure in reinforcement learning
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• The Markov Transition Constraint

This page was built for publication: Shaping reward signals in reinforcement learning using constraint programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6897960)