Train by individual steps

[tqwewe]

Is it possible to train a single step at a time, so I can have it run within something like a bevy system?

It seems like the current train method is usually done with a certain amount of iterations, but perhaps a function step or train_step would be convenient?

[milanboers]

You could use FixedIterations::new(0) as your termination strategy.

You can repeatedly call AgentTrainer.train and it will continue with the currently learned values.