Learning reward machines: a study in partially observable reinforcement learning

DOI10.1016/j.artint.2023.103989arXiv2112.09477OpenAlexW4385462630MaRDI QIDQ6080653

Rodrigo Toro Icarte, Toryn Qwyllyn Klassen, Sheila A. McIlraith, Margarita P. Castro, Richard Valenzano, Ethan Waldie

Publication date: 4 October 2023

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

Full work available at URL: https://arxiv.org/abs/2112.09477

zbMATH Keywords

reinforcement learningpartial observabilitynon-Markovian environmentsabstractionsautomata learningreward machines

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Learning regular sets from queries and counterexamples
• \({\mathcal Q}\)-learning
• Challenges of real-world reinforcement learning: definitions, benchmarks and analysis
• Learning Moore machines from input-output traces
• Convex Optimization: Algorithms and Complexity
• Complexity of automaton identification from given data
• Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Learning reward machines: a study in partially observable reinforcement learning