Metagame is the brainchild of Barney Pell <[email protected]>.
| Jay : game learning : Metagame |
His idea is that the task of writing a program to play a single game well is too narrow for artificial intelligence. It encourages you to rely on methods that work only for that game. A better task, he suggests, is to write a metagame program, a program that plays many games. You provide the program with the rules of a game, and the program tries to figure out how to play that game well. That way you're looking for good general-purpose methods, rather than good domain-specific hacks. A single-game program will play more strongly if it's well-tuned to that game, while a metagame program will play more strongly if it's smart.
I think it's a great idea. Work on machine learning of metagames could advance the overall state of the art in artificial intelligence. The class of games is broad, so a learning method that works well over a wide range of games is likely to work well in other formal domains too.
Getting down to details, Barney Pell proposed a class of what he calls "symmetric chess-like games," and he wrote software, the Metagame Workbench, to handle them. The Workbench reads and writes rule sets of symmetric chess-like games, generates random games, and includes several Metagame player programs, from simple to sophisticated.
Although the metagame idea is elegant, the class of symmetric chess-like games is ad hoc. The definition of the class is long and complicated and full of special cases. Its purpose is to make it possible to write an automatic game generator which creates comprehensible, playable games. Once the rules are generated, the game-playing system can translate them into a simpler, more general form, such as the Game Description Language in the Metagame Workbench, or the "game of abstract mathematical relations" proposed in the Morph project.
The Metagame Workbench software is written in Prolog (it runs under either Sicstus or Quintus Prolog). That makes it useful for exploring and experimenting with Metagame, but not useful for writing high-performance Metagame player programs. That doesn't detract from the concept--Prolog is a good language for exploration and research--but it hurts the flash value (it's easier to make a snazzy demo if you have a fast program), and it may make life a little harder if you want to try a computationally-expensive learning method.
The links below point to a UK Barney Pell papers ftp site which contains most of the information of the former Metagame ftp site.
Metagame: A new challenge for games and learning
(1992, 10 pages)
Barney Pell
Compressed postscript.
A general discussion of the metagame idea and its motivation.
Metagame in symmetric chess-like games (1992, 21 pages)
Barney Pell
Compressed postscript.
The definition of symmetric chess-like games, the random
game generator, and a sample generated game called
turncoat-chess.
Strategy Generation and Evaluation for Meta-Game Playing
Barney Pell
Compressed postscript.
A hefty PhD thesis with all the details, including a discussion of
Metagame player programs.
A strategic metagame player for general chess-like games
Barney Pell
Web page.
It's about a system that automatically generates the evaluation function
for a metagame directly from the rules, with no playing experience.
Metagame
This now-defunct web page was about
Danny Cron's Masters work on Metagame, at
Monash University in Australia.
About the Values of Chess Pieces
Ralph Betza
A web page investigating the strength of various chess pieces
and fairy chess pieces, part of a site about
chess variants (see the
Chess Variant Pages for more on fairy chess).
This shows how hard the job is that Pell took on in
"A strategic metagame player for general chess-like games", above.
