Tic-Tac-Toe the Hard Way
by People + AI Research
July 23, 2020 1:58 am
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.
Recent Episodes
Introducing Tic-Tac-Toe the Hard Way
4 years ago00:00/00:00Howdy, and the myth of “pouring in data”
4 years ago00:00/00:00What does a tic-tac-toe board look like to machine learning?
4 years ago00:00/00:00From tic-tac-toe moves to ML model
4 years ago00:00/00:00Beating random: What it means to have trained a model
4 years ago00:00/00:00Give that model a treat! : Reinforcement learning explained
4 years ago00:00/00:00Head to Head: the Big ML Smackdown!
4 years ago00:00/00:00Enter tic-tac-two
4 years ago00:00/00:00Head to Head: The Even Bigger ML Smackdown!
4 years ago00:00/00:00Lessons learned
4 years ago00:00/00:00