Real-time Interactive Gaming
Active from 1997 - 1999
In standard neuro-evolution, the objective is to evolve a network that best handles a given task. Although this approach is useful for static tasks, it does not work well in real-time domains where the environment (and therefore the task) can vary. Furthermore, if the real-time domain is interactive, the task is unpredictable because the user can change his/her behavior at will. We have tackled this problem by introducing a method for real-time interactive neuro-evolution, and testing the method through a real-time interactive gaming scenario. As the environment changes, the population evolves along with it and can cope with the task. We show that this method is superior to standard neuro-evolution techniques in the paper below. Please see the Animated Demo.

Adrian Agogino is also a member of this project.

Kenneth Stanley Postdoctoral Alumni kstanley [at] cs ucf edu
Computational Intelligence in Games Risto Miikkulainen, Bobby D. Bryant, Ryan Cornelius, Igor V. Karpov, Kenneth O. Stanley, and Chern H... In Gary Y. Yen and David B. Fogel, editors, Computational Intelligence: Principles and Practice<... 2006

Creating Intelligent Agents in Games Risto Miikkulainen The Bridge:5-13, 2006. 2006

Online Interactive Neuro-Evolution Adrian Agogino, Kenneth O. Stanley, and Risto Miikkulainen Neural Processing Letters:29-38, 2000. 2000