Planning with Abstract Learned Models While Learning Transferable Subtasks
Loading...
Links to Files
Author/Creator ORCID
Date
2020-03-04
Type of Work
Department
Program
Citation of Original Publication
Winder, J., Milani, S., Landen, M., Oh, E., Parr, S., Squire, S., desJardins, M., & Matuszek, C. (2020). Planning with Abstract Learned Models While Learning Transferable Subtasks. Proceedings of the AAAI Conference on Artificial Intelligence, 34(06), 9992-10000. https://doi.org/10.1609/aaai.v34i06.6555
Rights
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Subjects
Abstract
We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical models. We also demonstrate the increased potential for learned models to be transferred to new and related tasks.