Machine Learning in Games

How computers can learn to get better at playing games.

This site is for artificial intelligence researchers and intrepid game programmers. I describe game programs and their workings; they rely on heuristic search algorithms, neural networks, genetic algorithms, temporal differences, and other methods. I keep big list of online research papers. And there’s more.

Jay : game learning


- what’s new - updated 7 November 2013

- about these pages - including acknowledgements

find stuff here

find stuff in the rest of the world

- index of games mentioned on this site
- index of people mentioned on this site
- tutorials - get started with AI
- artificial intelligence links - the best entry points
- game links - about the games themselves
- game AI stuff - discussions, archives, etc.


learning projects and game-playing programs

- Internet distributed learning - machine learning @ home
- Metagame and General Game Playing - game-definition frameworks
- Morph - an ambitious project that includes game learning
- robotic soccer - with both simulated and real robots

- the neural network backgammon programs
- the strong learning othello programs
- pursuit-evasion games - various papers

- Nici Schraudolph’s go networks
- Sebastian Thrun’s NeuroChess
- Michael Gherrity’s SAL - a game-learning system

- Turing Test - the BotPrize, a Turing Test for Unreal Tournament, was won in 2012


methods

Here the emphasis is on the technique rather than the use it’s put to.

- evolutionary methods - aka genetic algorithms
- search algorithms - including rational search

- ideas to try out - playout analysis, learning methods, etc.


big lists of things

Everything that I didn’t write about above gets brief mention here. There’s lots of it!

- meetings - the most relevant workshops and conferences

- interesting web pages and less-interesting pages
- historical interest items - only a few, but they’re cool

- online papers - many of them!
- online software

- a thorough bibliography by Johannes Fürnkranz



Jay Scott <jay@satirist.org>
updated 7 November 2013