Also probably an issue of salience bias - you hear about virtually every plane crash and a lot of shootings, but road fatalities rarely make the news.

That speaks to the lack of good, standardized benchmarks for RL, more than anything else.

(Disclaimer: haven’t read the papers yet)

I agree completely. I just think the challenge will remain policy and public perception regarding public transit, same as it is today - just amplified by the effort that's been put into the technology by car manufacturers.

This is actually something that worries me - how can we ensure that all the progress in autonomous driving doesn't just put a lot more single-person cars on the road? And also, how do we convince people that this isn't an alternative, and that we need to keep investing in transit.

Been thinking about building a replacement for the arXiv daily email for a while, this looks like it might save me the trouble :)

Just out of curiosity: what’s the action space here?

Let’s use the real data to improve the simulators and get better massive, procedurally generated data 🤩