Neuroevolution in Games: State of the Art and Open Challenges
It provides a comprehensive overview for researchers and practitioners in AI and game development, but is incremental as a survey paper.
This paper surveys the application of neuroevolution (NE) to games, analyzing it across five axes such as network types and fitness determination, and identifies key open research challenges in the field.
This paper surveys research on applying neuroevolution (NE) to games. In neuroevolution, artificial neural networks are trained through evolutionary algorithms, taking inspiration from the way biological brains evolved. We analyse the application of NE in games along five different axes, which are the role NE is chosen to play in a game, the different types of neural networks used, the way these networks are evolved, how the fitness is determined and what type of input the network receives. The article also highlights important open research challenges in the field.