OpenNERO
Released 2010
OpenNERO is a general research and education platform for artificial intelligence. The platform is based on a simulation and graphical display of a 3-D physical world that includes multiple agents with embedded sensors and effectors and multiple objects. The software also includes tools for defining and manipulating the environment, the task, and the agent algorithms. The OpenNERO software environment allows developing and testing new AI methods as well as demonstrating existing methods in a sophisticated and concrete simulation of the physical world.

An abstract of the OpenNERO demo presented at AIIDE-08 is here. The current version of the environment is maintained at Googlecode. An example machine learning game that serves as inspiration for OpenNERO is described the NERO page.

Download:
TAR
Adam C. Dziuk Undergraduate Alumni
Igor V. Karpov Ph.D. Student ikarpov [at] gmail com
Dan Lessin Ph.D. Student dlessin [at] cs utexas edu
Risto Miikkulainen Faculty risto [at] cs utexas edu
Kenneth Stanley Postdoctoral Alumni kstanley [at] cs ucf edu
IJCNN-2013 Tutorial on Evolution of Neural Networks 2013
Risto Miikkulainen, To Appear In unpublished. Tutorial slides..
Creating Intelligent Agents through Shaping of Coevolution 2011
Adam Dziuk and Risto Miikkulainen, In Proceedings of the Congress on Evolutionary Computation, New Orleans, LA 2011. IEEE.
Neuroevolution 2010
Risto Miikkulainen, In Encyclopedia of Machine Learning, New York 2010. Springer.
The Necessity of Separating Control and Logic When Grounding Language Using Neuroevolution 2009
Yonatan Bisk, Technical Report HR-09-05, Department of Computer Sciences, The University of Texas at Austin.
Real-time Neuroevolution in the NERO Video Game 2005
Kenneth O. Stanley, Bobby D. Bryant, and Risto Miikkulainen, IEEE Transactions on Evolutionary Computation (2005), pp. 653-668. IEEE.