Episode 06 / Written companion
Customer recording trackRMA in my own JAX sim, and a throw
A privileged teacher, a history-only student and a new reward that throws a ping-pong ball, all in the sim you wrote.
Read the companion now. The recording is forthcoming; “Customer” identifies its planned release track.
Free account
Read the full companion.
This companion is on the customer track. The course is free: create an account to read it, together with every lesson, lab and gate.
Put the idea to work
Adaptation without knowing the physics
Train a privileged policy with PPO across thousands of randomized arms, then distill what it knew into an adaptation module that reads only the 50-step history. Compare it with Variant B and the Module 3 EKF, and reuse the same trainer to throw a ball into a cup.
Build module 05