Art of the Problem | How Board Games Revolutionized AI: The Evolution of Value Functions @ArtOfTheProblem | Uploaded 4 weeks ago | Updated 11 hours ago
I explore the development of Value functions in AI/Machine Learning applied to chess, checkers and backgammon. I always found it confusing learning about Value functions, Policy functions, Q learning...etc The key reason was I was learning backwards, and so this is an attempt to explain value functions by following the true history. Shannon, Samuel, Tesauro
This is just a snippet of my full video on RL: youtube.com/watch?v=Dov68JsIC4g
I explore the development of Value functions in AI/Machine Learning applied to chess, checkers and backgammon. I always found it confusing learning about Value functions, Policy functions, Q learning...etc The key reason was I was learning backwards, and so this is an attempt to explain value functions by following the true history. Shannon, Samuel, Tesauro
This is just a snippet of my full video on RL: youtube.com/watch?v=Dov68JsIC4g