IJCNN-2013 Tutorial on Evolution of Neural Networks (2013)

Neuroevolution, i.e. evolution of artificial neural networks, has
recently emerged as a powerful technique for solving challenging
reinforcement learning problems. Compared to traditional
(e.g. value-function based) methods, neuroevolution is especially
strong in domains where the state of the world is not fully known: The
state can be disambiguated through recurrency, and novel situations
handled through pattern matching. In this tutorial, I will review (1)
neuroevolution methods that evolve fixed-topology networks, network
topologies, and network construction processes, (2) ways of combining
traditional neural network learning algorithms with evolutionary
methods, and (3) applications of neuroevolution to control, robotics,
artificial life, and games.

A link to the slides is below.

See also the Scholarpedia article on neuroevolution.

Citation:

To Appear In 2013. Tutorial slides..
Bibtex:

Presentation:

Slides
(PDF)
[Expand to show all 15]

Multi-modal Approaches to Evolving Behavior for Multi-task Games | Jacob Schrum | 2011 |

The Role of Reward Structure, Coordination Mechanism and Net Return in the Evolution of Cooperation | Padmini Rajagopalan, Aditya Rawal | 2011 |

Emergence of Competitive and Cooperative Behavior and Arms Race Through Coevolution | Aditya Rawal, Padmini Rajagopalan | 2010 |

Evolving Controller Symmetry for Multilegged Robots | Vinod Valsalam | 2010 |

Fitness-based Shaping in Multi-objective Domains | Jacob Schrum | 2010 |

Learning in Fractured Domains | Nate Kohl | 2009 |

Multi-modal Behavior in NPCs | Jacob Schrum | 2009 |

Multi-objective Neuroevolution of NPCs | Jacob Schrum | 2008 |

Evolving Cooperation in Multiagent Systems | Chern Yong | 2007 |

Neuro-Evolving Robotic Operatives (NERO) | Kenneth Stanley | 2007 |

Adaptive Teams of Agents in the Legion II game | Bobby Bryant | 2006 |

Evolving Vehicle Warning Systems | Nate Kohl | 2006 |

Finless Rocket Control | Faustino Gomez | 2003 |

Neuroevolution of Augmenting Topologies Demos | Kenneth Stanley | 2003 |

Double Pole Balancing with ESP | Faustino Gomez | 1999 |

ENSO | This package contains software implementing the ENSO approach for evolving symmetric modular neural networks. It also in... | 2010 |

NEAT C++ | The NEAT package contains source code implementing the NeuroEvolution of Augmenting Topologies method. The source code i... | 2010 |

OpenNERO | OpenNERO is a general research and education platform for artificial intelligence. The platform is based on a simulatio... | 2010 |

rtNEAT C++ | The rtNEAT package contains source code implementing the real-time NeuroEvolution of Augmenting Topologies method. In ad... | 2006 |

ESP JAVA 1.1 | The ESP package contains the source code for the Enforced Sup-Populations system written in Java. This package is a near... | 2002 |

NEAT Java (JNEAT) | The JNEAT package contains Java source code for the NeuroEvolution of Augmenting Topologies method (see the original | 2002 |

ESP C++ | The ESP package contains the source code for the Enforced Sup-Populations system written in C++. ESP is an extension t... | 2000 |