Hacker News new | ask | show | jobs
by hotwire 1812 days ago
It reminds me of the thread about the Quake 3 bots, who left alone for several years, figured out that the best approach was to not kill each other.

https://i.imgur.com/dx7sVXj.jpg

1 comments

Without knowledge of their reward function its difficult to tell if they're converged on this strategy or if its just broken.