Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer
This work addresses ARC challenges for AGI research, but it is incremental as it builds on existing methods like Decision Transformers.
The authors tackled Abstraction and Reasoning Corpus (ARC) tasks to advance artificial general intelligence by using a Decision Transformer with imitation learning and a novel object detection method, achieving enhanced problem-solving skills but noting limitations in data and models.
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.