Planning with Abstract Learned Models While Learning Transferable Subtasks

• DOI: 10.1609/aaai.v34i06.6555
• Publication Date: 2020-06-29T18:58:21Z
• Authors: John Winder; Stephanie Milani; Matthew Landen; Erebus Oh; Shane Parr; Shawn Squire; Marie DesJardins; Cynthia Matuszek
• Keywords: Abstraction

We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable probabilistic planning at multiple levels of abstraction. 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 that are independent modular. Through our experiments, we show how integrates execution, facilitating rapid efficient abstract, models. also demonstrate increased potential learned be transferred related tasks.