Competitions provide an ideal opportunity for you to test your algorithms and
architectures and compare them against the best that other researchers around
the globe can offer. The multi-objective optimization competition is closed now,
but the game-related competitions will remain open until just before the
conference. The winner of each competition will get to present their methods in
a special competition session, receive a USD500 prize and certificate to
be presented at the conference banquet, and get a mention in IEEE Computational
There are four games: Neural Network Othello, Car Racing, Ms. Pac-Man, and X-Pilot AI. The first two are relatively straightforward to enter, while the latter two require more programming effort. All are great fun, and scientifically interesting.
To be run, each competition requires at least five distinct entrants; competitions with insufficient entries will be cancelled.
Similar versions of the game-related competitions were also run for IEEE CIG 2007, and a modified simulated car racing competition is also being run for FUZZ-IEEE 2007. This is a deliberate attempt to foster more participation in the competitions by allowing greater continuity.
We warmly encourage you to participate, and make these a great success.
Unlike Pac-Man, Ms. Pac-Man is a non-deterministic game, and rather difficult for most human players. As far as we know, nobody really knows how hard it is to develop an AI player for the game. The world record for a human player (on the original arcade version) currently stands at 921,360 (read more). Can anyone develop a software agent to beat that?
The Ms. Pac-Man competition will use the Microsoft Revenge of Arcade version to test the ability of computer-based players at the conference. We are especially interested in players that use computational intelligence methods to address the problem, but the contest is open to any type of algorithm: you can hand-program it as much as you like.
The mode of interaction is as follows: about 15 times per second your program will be sent a pixel map of the Ms. Pac-Man window, and it then responds with an integer indicating the direction of the joystick.
More details together with the current version of the toolkit are available here.
This competition also ran successfully at IEEE CEC 2006. The goal of this competition is to supply the winning evaluation (utility) function for Othello (also known as Reversi).
The scientific aims of the competition are to further our understanding of which
type of architecture is best for performing Othello position evaluation, of
which learning methods work best, and the level of play that can be achieved at
Please follow this link: http://algoval.essex.ac.uk:8080/othello/html/Othello.html
Organised by Simon Lucas and Thomas Runarsson.
X-Pilot is a hugely popular on-line 2-d space war game - a bit like multi-player Asteroids.
The details of the CIG competition are currently being finalised, but entrants will supply complete X-Pilot player bots; these can be hand programmed or evolved, or trained in some other way.
For more details see here.
Organised by Gary Parker and Matt Parker.
aim of this competition is to design the best performing controller for
a simulated car. The racing is point-to-point against an opponent car,
and the challenge mixes driving skill with game strategy. The waypoints
must be hit in order, but once a waypoint has been hit by one car, the
next one becomes active. Therefore, a controller may decide to skip a
waypoint and head directly for the one after it. The setup for the
competition has been made especially simple to encourage maximum
participation, but the game is still very challenging. More details
Organised by Julian Togelius.
This competitions will evaluate multi-objective optimization algorithms on a suite of common benchmark problems. This competition is closely associated with the CEC 2007 special session on the same subject. More details available here: http://www.ntu.edu.sg/home/epnsugan