Towards an Evolutionary Approach for Exploting Core Knowledge in Artificial Intelligence
Andrea Calabrese, Stefano Quer, Giovanni Squillero, Alberto Paolo Tonda · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2024
This paper presents a proof of concept for a novel evolutionary methodology inspired by core knowledge. This theory describes human cognition as a small set of innate abilities combined through compositionality. The proposed approach generates predictive descriptions of the interaction between elements in simple 2D videos. It exploits well-known strategies, such as image segmentation, object detection, simple laws of physics (kinematics and dynamics), and evolving rules, including high-level classes and their interactions. The experimental evaluation focuses on two classic video games, Pong and Arkanoid. Analyzing a small number of raw video frames, the methodology identifies objects, classes, and rules, creating a compact, high-level, predictive description of the interactions between the elements in the videos.