Learning Portable Representations for High-Level Planning
This addresses the challenge of sample-efficient transfer learning in AI planning, though it appears incremental in its approach.
The paper tackles the problem of learning portable abstract representations for high-level planning across low-level continuous environments, demonstrating that agents can transfer learned symbolic vocabularies and rules to new tasks, which reduces the number of samples required for representation learning.
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 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 number of samples required to learn a representation of a new task.