One way I could write a computer program that e.g. lands a rocket ship is to simulate many landings that could happen after possible control inputs, pick the simulated landing that has properties I like ( such as not exploding and staying far from actuator limits) and then run a low latency loop that locally makes reality track that simulation, counting on the simulation to reach a globally pleading end.
Is this what you mean by loading something into your pseudo prediction?
One way I could write a computer program that e.g. lands a rocket ship is to simulate many landings that could happen after possible control inputs, pick the simulated landing that has properties I like ( such as not exploding and staying far from actuator limits) and then run a low latency loop that locally makes reality track that simulation, counting on the simulation to reach a globally pleading end.
Is this what you mean by loading something into your pseudo prediction?
This is just straight-up planning and doesn’t require doing weird gymnastics to deal with a biological brain’s broken type system.