Control researcher: most people can't do system modeling, so RL is strictly easier — but claims are overstated
KyleMorgenstein · x · 2026-10-02
Kyle Morgenstein continues the RL vs classical control debate: most people are bad at controls and worse at system modeling, making RL strictly easier (copy-paste rewards and hyperparameters help). He thinks RL is the right default tool, but says the original claims are overstated.
Related event: Robotics Researchers Debate Whether RL Beats Classical Control(4 posts)→
More from Embodied
- Hugging Face LeRobot adds humanoid support: π0.5 policy drives 29-DoF Unitree G1 — freelerobot · 2026-10-02
- Researcher's blunt verdict on humanoids: "The robots do not work" — andrew_n_carr · 2026-10-02
- Robot's Early Taichi Policy Trained on Kaggle Shows Promising Kung Fu Moves — freelerobot · 2026-10-02
- BeyondSCe grasps objects by past-event reference, hitting 77% success on occluded targets — SeoulNationalUniv · 2026-10-02
- NUS's APPL uses structural priors to bridge skill learning and composition in robot manipulation — NationalUniversityofSingapore · 2026-10-02
- Open-source Harness fork moves coding agents out of the app into orca — dee_hw · 2026-10-02