Reward-respecting subtasks for model-based reinforcement learning

DOI10.1016/j.artint.2023.104001arXiv2202.03466OpenAlexW4386484398MaRDI QIDQ6088325

Finbarr Timbers, David Szepesvari, Brian K. Tanner, G. Zacharias Holland, Adam White, Richard S. Sutton, Marlos C. MacHado

Publication date: 16 November 2023

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

Full work available at URL: https://arxiv.org/abs/2202.03466

zbMATH Keywords

optionsplanningmodel-based reinforcement learningtemporal abstractionfeature attainmentSTOMP progression

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• Unnamed Item
• Automatically generating abstractions for planning
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Planning in a hierarchy of abstraction spaces
• Diversity-based inference of finite automata
• OnActor-Critic Algorithms
• From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning

This page was built for publication: Reward-respecting subtasks for model-based reinforcement learning