Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer

Jaehyun Park, Jaegyun Im, Sanha Hwang, Mintaek Lim, Sabina Ualibekova, Sejin Kim, Sundong Kim

Keywords: Abstraction and Reasoning Corpus, Imitation Learning, Object-centric Learning, Artificial General Intelligence

TL;DR: We mimic human problem solving strategy on Abstracion and Reasoning Challenge (ARC) with object-centric imitation learning, prompting further AGI advancements.

Abstract:

In the pursuit of artificial general intelligence (AGI), we tackle Abstraction and Reasoning Corpus (ARC) tasks using a novel two-pronged approach. We employ the Decision Transformer in an imitation learning paradigm to model human problem-solving, and introduce an object
detection algorithm, the Push and Pull clustering method. This dual strategy enhances AI’s ARC problem-solving skills and provides insights for AGI progression. Yet, our work reveals the need for advanced data collection tools, robust training datasets, and refined model structures. This study highlights potential improvements for Decision Transformers and propels future AGI research.

Submission Number: 28