find a way to optimize AI loading times

TensorFlow takes minutes to import on a Raspberry Pi Zero W and that's probably because of the huge .so file with native primitives it has to load, among other things. Given the nature of the project, that stuff is imported only once, so caching it in memory wouldn't speed things up. Switching frameworks is not feasible, unless we have the same exact features (unlikely given that stable-baselines is TF based). For instance, there's no stable-baselines port for TF-lite.