Long-Range Robotic Navigation via Automated Reinforcement Learning

I am happy to see that surrogate model optimization is starting to be used to its potential, but it's sad to have to watch it from the sidelines.

This is no doubt exciting, but I am curious how well they deal with unexpected obstructions (such as cars at intersections behaving in unexpected fashion). Remember, we have a lot of issues with self-driving, and the kind of problems (not quite handling environment correctly) are translatable to this use case as well...