Subscribe
Share
Share
Embed
David’s variant of tic-tac-toe that we’re calling tic-tac-two is only slightly different but turns out to be far more complex. This requires rethinking what the ML system will need in order to learn how to play, and how to represent that data.
A writer and a software engineer from Google's People + AI Research team explore the human choices that shape machine learning systems by building competing tic-tac-toe agents.