Abstract:
In the NeuroEvolving Robotic Operatives (NERO) game, the player trains a team of virtual robots for combat against other players' teams. The virtual robots learn in real time through interacting with the player. Since NERO was originally released in June, 2005, it has been downloaded over 50,000 times, appeared on Slashdot, and won several honors. A significant update was released in November, 2005, including improved performance, new battle mode options, and faster learning. The virtual robots learn using the real-time NeuroEvolution of Augmenting Topologies (rt-NEAT) method, which can evolve increasingly complex artificial agents in NERO adapt in real time as they interact with the player in the new, updated game. In the future, rtNEAT may allow new kinds of educational and training applications through interactive and adapting games.
DOI:
10.1609/aiide.v2i1.18771