Learning Portable Representations for High-Level Planning

Part of Proceedings of the International Conference on Machine Learning 1 pre-proceedings (ICML 2020)

Bibtex »Metadata »Paper »Supplemental »

Authors

Steven James, Benjamin Rosman, George Konidaris

Abstract

We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments. We show that these abstract representations can be learned in a task-independent egocentric space \textit{specific to the agent} that, when grounded with problem-specific information, are provably sufficient for planning. We demonstrate transfer in two different domains, where an agent learns a portable, task-independent symbolic vocabulary, as well as rules expressed in that vocabulary, and then learns to instantiate those rules on a per-task basis. This reduces the samples required to learn a representation of a new task.