Advanced Approach to Play a Atari Game

Addresses the challenge of learning to play many different video games with little domain-specific knowledge. It introduces a neuroevolution approach to general Atari 2600 game playing. Four neuroevolution algorithms were paired with three different state representations and evaluated on a set of 61 Atari games. The neuroevolution agents represent different points along the spectrum of algorithmic sophistication - including weight evolution on topologically fixed neural networks (conventional neuroevolution),covariance matrix adaptation evolution strategy (CMA?ES), neuroevolution of augmenting topologies (NEAT), and indirect network encoding (HyperNEAT).These results suggest adaptation evolution strategy (CMA?ES), neuroevolution of augmenting topologies (that neuroevolution is a promising approach to general video game playing (GVGP).