Learning in Fractured Domains (2009)
Author: Nate Kohl
Hand-coded keepaway policy:


Keepaway policy evolved with Cascade-NEAT:


Half-field soccer policy evolved with Cascade-NEAT:
People
Nate Kohl Ph.D. Alumni nate [at] natekohl net
Risto Miikkulainen Faculty risto [at] cs utexas edu
Projects
Constructing Intelligent Agents in Simulated Worlds 2008 - 2010
Learning Strategic Behavior in Sequential Decision Tasks 2009 - 2014
Publications
IJCNN-2013 Tutorial on Evolution of Neural Networks 2013
Risto Miikkulainen, To Appear In unpublished. Tutorial slides..
Evolving Neural Networks for Strategic Decision-Making Problems 2009
Nate Kohl and Risto Miikkulainen, Neural Networks, Special issue on Goal-Directed Neural Systems (2009).
Evolving Neural Networks for Fractured Domains 2008
Nate Kohl and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference, pp. 1405-1412, July 2008.
Related Areas
Neuroevolution Reinforcement Learning
Labs
Neural Networks