Real-time evolution of neural networks in the NERO video game

Abstract

A major goal for AI is to allow users to interact with agents that learn in real time, making new kinds of in-teractive simulations, training applications, and digital entertainment possible. This paper describes such a learning technology, called real-time NeuroEvolution of Augmenting Topologies (rtNEAT), and describes how rtNEAT was used to build the NeuroEvolving Robotic Operatives (NERO) video game. This game represents a new genre of machine learning games where the player trains agents in real time to perform challenging tasks in a virtual environment. Providing laymen the capabil-ity to effectively train agents in real time with no prior knowledge of AI or machine learning has broad impli-cations, both in promoting the field of AI and making its achievements accessible to the public at large.