Leveraging Structures in Evolutionary Neural Policy Search

Paul Templier · ACM SIGEVOlution · 2025

Training agents to perform complex tasks like driving a car, mastering a video game, or controlling a robot to walk presents a significant challenge when expert demonstrations are not available. In nature, complex behaviors and characteristics can emerge through evolution, as animals adapt to their environments and problems over generations.

Read the paper · More papers on PaperTik