Wow, that’s really new, within the last few months, thanks for the link. The challenge sounds smaller than it was. It had been worked on for years prior, as I mentioned with poor results.
Now on to Starcraft 2, where some major research labs are competing including DeepMind.
“latching on to”? It’s not about trying to disrespect the research, or downplay the capabilities of AI after the last decade’s amazing progress.
It’s about noting all the little milestones and unsolved problems along the way, not just the headlines. The idea is to improve perspective on the whole of where the state of the art is.
As for the next game, I don’t imagine it will be too many years before we reach the 99% percentile of AI playing all games at least as well as the best humans. Why not throw out a prediction? Less than 5 years?
