Autonomous Learning of Object-Centric Abstractions for High-Level Planning

Steven James, Benjamin Rosman, George Konidaris

Keywords: reinforcement learning, planning, PDDL, multitask, transfer, objects

Abstract: We propose a method for autonomously learning an object-centric representation of a continuous and high-dimensional environment that is suitable for planning. Such representations can immediately be transferred between tasks that share the same types of objects, resulting in agents that require fewer samples to learn a model of a new task. We first demonstrate our approach on a simple domain where the agent learns a compact, lifted representation that generalises across objects. We then apply it to a series of Minecraft tasks to learn object-centric representations, including object types—directly from pixel data—that can be leveraged to solve new tasks quickly. The resulting learned representations enable the use of a task-level planner, resulting in an agent capable of forming complex, long-term plans with considerably fewer environment interactions.

One-sentence Summary: We show how to learn an object-centric representation from pixels that can be used by a classical planner.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ieK_b1ofIO