Learning Object-Centric Representations for High-Level Planning in Minecraft

Steven James, Benjamin Rosman, George Konidaris
July 2020
PDF Cite Project

Abstract

We propose a method for autonomously learning an object-centric representation of a highdimensional environment that is suitable for planning. Such abstractions can be immediately 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 demonstrate our approach on a series of Minecraft tasks to learn object-centric representations—directly from pixel data—that can be leveraged to quickly solve new tasks. The resulting learned representations enable the use of a task-level planner, resulting in an agent capable of forming complex, long-term plans

Type
Workshop paper
Publication
Object-Oriented Learning: Perception, Representation, and Reasoning. Workshop at ICML
Symbolic Representations Reinforcement Learning Classical Planning Transfer Learning
Steven James
Steven James
Deputy Lab Director

My research interests include reinforcement learning and planning.

Benjamin Rosman
Benjamin Rosman
Lab Director

I am a Professor in the School of Computer Science and Applied Mathematics at the University of the Witwatersrand in Johannesburg. I work in robotics, artificial intelligence, decision theory and machine learning.