Small World Models - by Ben Recht - arg min
argmin.net · 987 words · saved by 1 readers
How much do you need to know about a system to control it?
Small World Models How much do you need to know about a system to control it? Ben Recht Mar 16, 2026 30 3 2 Share This is a live blog of Lecture 6 of my graduate seminar “Feedback, Learning, and Adaptation.” A table of contents is here . The backbone of control engineering is the assumption of a reasonably reliable, reasonably simple dynamical system with inputs and outputs. We have to believe that the behavior of the thing we want to steer is consistent enough so that whatever we design in the lab will work on the road. Now, what exactly do I need to know about this reliably consistent dynami
saved by
related reading
- Study Guide — LessWronglesswrong.com
- Control theory - Wikipediaen.wikipedia.org
- Picking a Control Strategydocs.wpilib.org
- State of Robot Learning, December 2025vedder.io
- Highly optimized optimizers - by Ben Recht - arg minargmin.net
- Spring 2023 6.8210 Lecture 2: Nonlinear Dynamicsyoutube.com
- pdfopenreview.net
- Reinforcement Learning: Machine Learning Meets Control Theoryyoutube.com
- Reformist Reinforcement Learning - by Ben Recht - arg minargmin.net
- How Can We Make Robotics More like Generative Modeling? | Eric Jangevjang.com
- 16831_lecture09_beckart.pdfcs.cmu.edu
- World Models | Rohit Bandarurohitbandaru.github.io