Evolving simple programs for playing Atari games
This work addresses the challenge of developing efficient game-playing agents for the Atari benchmark set, though it is incremental as it applies an existing method to a new domain.
The researchers tackled the problem of playing Atari games by evolving small programs using Cartesian Genetic Programming, resulting in controllers that are competitive with state-of-the-art methods and require less training time.
Cartesian Genetic Programming (CGP) has previously shown capabilities in image processing tasks by evolving programs with a function set specialized for computer vision. A similar approach can be applied to Atari playing. Programs are evolved using mixed type CGP with a function set suited for matrix operations, including image processing, but allowing for controller behavior to emerge. While the programs are relatively small, many controllers are competitive with state of the art methods for the Atari benchmark set and require less training time. By evaluating the programs of the best evolved individuals, simple but effective strategies can be found.