Evolutionary Computation Technical Committee : Games Working Group
Games provide competitive dynamic environments that make ideal test-beds for computational intelligence theories, architectures, and algorithms. Natural evolution can be considered a game, where the rewards for an organism that plays a good game of life are the propagation of its genetic material to its successors. In natural evolution, the fitness of an individual is defined with respect to its competitors and collaborators, as well as the environment. Within the evolutionary computation (EC) literature, this is known as co-evolution, and within this paradigm expert game-playing strategies have been evolved without the need for human expertise.
Much of the early work on computational intelligence and games was directed towards classic board games, such as tic-tac-toe (noughts and crosses), chess, and checkers (draughts), but in most board games, computers now far out-class human players. A game that has so far resisted machine attack is Go, where the best computer players now play at the level of a good novice. Go strategy seems to rely as much on pattern recognition as it does on logical analysis, and the large branching factor severely restricts the look-ahead that can be used within a game-tree search.
Games also provide interesting abstractions of real-world situations, a classic example being Axelrod's Prisoner's Dilemma. Of particular interest to the computational intelligence community, is the iterated version of this game (IPD), where plays can devise strategies that depend on previous behaviour. A version of IPD was run as a competition for 2004 Congress on Evolutionary Computation, and a different version will be used for the CIG 2005 competition.
In recent years, researchers have been applying EC methods to evolving all kinds of game-players, including real-time arcade and console games (e.g. Quake, Pac-Man). There are many goals to this research, and one emerging theme is using EC to generate opponents that are more interesting and fun to play against, rather than being necessarily superior.
This working group is dedicated to promoting all types of
interplay between games and evolutionary computation.
There are the following games WG events in 2005:
There are some game competitions associated with IEEE CIG 2005 - see here.
Please contact me with any suggestions for this working group.
Simon M. Lucas