Joint learning of reward machines and policies in environments with partially known semantics

DOI10.1016/J.ARTINT.2024.104146zbMATH Open1543.6832MaRDI QIDQ6579299FDOQ6579299

Authors: Christos K. Verginis, Cevahir Koprulu, Sandeep Chinchali, Ufuk Topcu 

Publication date: 25 July 2024

Published in: Artificial Intelligence (Search for Journal in Brave)

Recommendations

• Learning reward machines: a study in partially observable reinforcement learning
• Reward machines: exploiting reward function structure in reinforcement learning
• Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs
• Inverse reinforcement learning in partially observable environments
• Learning partially observable non-deterministic action models

zbMATH Keywords

reinforcement learningreward machinesperception limitations

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Formal languages and automata (68Q45) Computational learning theory (68Q32)

Cites Work

• PySAT: a Python toolkit for prototyping with SAT oracles
• \({\mathcal Q}\)-learning
• Title not available (Why is that?)
• Complexity of automaton identification from given data
• Exact DFA Identification Using SAT Solvers
• Omega-Regular Objectives in Model-Free Reinforcement Learning
• Reward machines: exploiting reward function structure in reinforcement learning

This page was built for publication: Joint learning of reward machines and policies in environments with partially known semantics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6579299)