RL practitioner: Neural networks are magic; failure is a skill issue

yacineMTB · x · 2026-08-27

A developer specializing in control RL shares that deep learning feels like magic. They argue that if given the right data, neural networks will learn, implying that failures usually stem from data quality or problem formulation (a skill issue) rather than the models themselves.

Related event: RL Researcher: Deep Learning Is Basically Magic(2 posts)→

Original post →

More from Research

Research channel →