A brief review of how AI was applied to games through the years, from the first game ever implemented to today's deep learning AlphaGo. Much of the context was in speaking, so see the accompanying blog post at: https://alteregozi.com/2016/09/17/learning-to-play/
Learning to Play: History of Machine Learning in Classic Games
1.
2. ARTIFICIAL INTELLIGENCE
Let’s start from the basics
Actually, let’s go straight to the cutting edge!
Here’s a demo for a multi-layered convolutional neural network
using feed-forward training to perform supervised learning
7. EARLY DAYS – MINIMAX
Build a tree of game states
(from current state)
Well-defined transition rules
Define a function to score each state
How close are we to the goal (a
winning board)?
Choose path that maximizes our gain
and minimizes opponent’s gains
10. 5 x 1020 (500 billion billion) possible positions
11.
12.
13.
14.
15. “With his passing, we lost not only a feared adversary but also a friend. Every member
of our team had the deepest respect and admiration for Tinsley. It was a privilege to
know him”
22. GENERIC LEARNING
So far, humans were central in the learning process
Pre-encoding the allowed moves
Providing the winning states
Can machines learn on their own, like real toddlers?
27. • We’re skipping entire ML courses now
• What’s fundamentally different about Deep Learning?
• No predefined rules – a generic system
• “A bishop moves this way, and a knight this way…”
• No domain knowledge – system “finds” the features
• “count #pieces within 3 steps from the king”
DEEP LEARNING
28. • We’re skipping even more entire ML courses now
• Uses Artificial Neural Network, with LOTS of data
• Deep Learning == multiple hidden layers
DEEP LEARNING
Magic happens HERE…
Magic built-in
32. GENERATIVE LANGUAGE MODELS
• Not done with skipping ML courses just yet
• First, let’s divert to literature for a bit, shall we?...
• “Robert Cohn was once middleweight boxi?”
https://medium.com/@ageitgey/machine-learning-is-fun-part-2-a26a10b68df3