Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer
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.
Cite
Text
Park et al. "Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer." ICML 2023 Workshops: ILHF, 2023.Markdown
[Park et al. "Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer." ICML 2023 Workshops: ILHF, 2023.](https://mlanthology.org/icmlw/2023/park2023icmlw-unraveling/)BibTeX
@inproceedings{park2023icmlw-unraveling,
title = {{Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer}},
author = {Park, Jaehyun and Im, Jaegyun and Hwang, Sanha and Lim, Mintaek and Ualibekova, Sabina and Kim, Sejin and Kim, Sundong},
booktitle = {ICML 2023 Workshops: ILHF},
year = {2023},
url = {https://mlanthology.org/icmlw/2023/park2023icmlw-unraveling/}
}