Episode 06 / Written companion

Customer recording track

RMA in my own JAX sim

Move from privileged training information to a history-only controller.

Read the companion now. The recording is forthcoming; “Customer” identifies its planned release track.

Put the idea to work

Adaptation without knowing the physics

Implement a two-stage RMA-style policy, then compare it with a policy using the frozen predictive encoder. Keep the compute, observation and deployment budgets visible.

Build module 05