Winder, JohnMilani, StephanieLanden, MatthewOh, ErebusParr, ShaneSquire, ShawndesJardins, MarieMatuszek, Cynthia2021-04-092021-04-092020-03-04Winder, 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.v34i06.6555https://doi.org/10.1609/aaai.v34i06.6555http://hdl.handle.net/11603/21314Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34 No. 06: AAAI-20 Technical Tracks 6, AAAI Technical Track: Planning, Routing, and SchedulingWe 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.9 pagesen-USThis 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.Text