Learning Classifier Systems as a Solver for the Abstraction and Reasoning Corpus
Cameron Coombe, David Howard, Will Neil Browne · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2024
The abstraction and reasoning corpus (ARC) is a challenging AI benchmark as it requires models to learn unseen relationships from a few data points. Each puzzle only contains 2--5 training examples, which makes it hard for models that require training on large datasets. Models which do not require training on large datasets like learning classifier systems (LCSs) have the potential to solve this kind of complex, low-data problem due to their flexible representation, niche-based learning, and ability to generalise. Whilst some learners that can operate on low data have been applied to ARC, LCS-based architectures remain entirely unexplored. We propose a simple LCS architecture employing a windowing approach. This architecture solves 19 of 400 test grids (4.75%) in the ARC training set, which shows promise by outperforming other naïve approaches. Additionally, the system uses minimal prior knowledge to achieve this result, bringing it closer to the original vision of an ARC solver, which is to only rely on a core set of concepts. We provide directions on how this basic model could be expanded upon to include more complex structures making use of LCSs' ability to integrate many diverse kinds of representations.