UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
admin
ESP C++
Released 2000
The ESP package contains the source code for the Enforced Sup-Populations system written in C++. ESP is an extension to the SANE algorithm that segregates the neurons into sub-populations, one for each hidden unit in the networks being evolved. This allows neuron specializations to form more rapidly through constrained mating and enables the system to evolve recurrent networks. This package applies ESP to a non-Markov version of the double pole balancing problem. This is a difficult control task that requires short-term memory. For more details on ESP and/or the double pole system, see this paper on ESP or others found under Neuroevolution Methods and Applications.
Download:
TAR
People
Faustino Gomez
Postdoc (Alumni)
inaki@cs.utexas.edu
Publications (13)
IJCNN-2013 Tutorial on Evolution of Neural Networks
2013
Risto Miikkulainen
Multiagent Learning through Neuroevolution
2012
Risto Miikkulainen, Eliana Feasley, Leif Johnson, Igor Karpov, Padmini Rajagopalan, Aditya Rawal, and Wesley Tansey
Coevolution of Role-Based Cooperation in Multi-Agent Systems
2010
Chern Han Yong and Risto Miikkulainen
Neuroevolution
2010
Risto Miikkulainen
Coevolution of Role-Based Cooperation in Multi-Agent Systems
2007
Chern Han Yong and Risto Miikkulainen
Computational Intelligence in Games
2006
Risto Miikkulainen, Bobby D. Bryant, Ryan Cornelius, Igor V. Karpov, Kenneth O. Stanley, and Chern Han Yong
Active Guidance for a Finless Rocket Using Neuroevolution
2003
Faustino J. Gomez and Risto Miikkulainen
Robust Non-Linear Control through Neuroevolution
2003
Faustino J. Gomez
Utilizing Domain Knowledge in Neuroevolution
2003
James Fan, Raymond Lau, and Risto Miikkulainen
A Neuroevolution Method For Dynamic Resource Allocation On A Chip Multiprocessor
2001
Faustino J. Gomez, Doug Burger, and Risto Miikkulainen
Solving Non-Markovian Control Tasks With Neuroevolution
1999
Faustino J. Gomez and Risto Miikkulainen
2-D Pole Balancing With Recurrent Evolutionary Networks
1998
Faustino Gomez and Risto Miikkulainen
Incremental Evolution Of Complex General Behavior
1997
Faustino Gomez and Risto Miikkulainen
Projects
Solving Non-Markov Control Tasks
1996 - 2006
Cooperative Coevolution of Multi-Agent Systems
2000 - 2007
Diverse Behavior in Teams of Homogeneous Agents
2001 - 2007
Controlling a Finless Rocket Through Neuroevolution
2002 - 2003
Learning Navigation for Personal Satellite Assistant using Neuroevolution
2004 - Present
Areas of Interest
Robotics
Neuroevolution
Artificial Life
Demos
Evolving Cooperation in Multiagent Systems
Chern Yong
2007
Finless Rocket Control
Faustino Gomez
2003
Adaptive Teams of Agents in the Legion II game
Bobby Bryant
2006
Double Pole Balancing with ESP
Faustino Gomez
1999
Labs
Neural Networks