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, we 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 game playing, robot control, resource optimization,
and cognitive science.
%0 Conference Paper
%1 Miikkuklainen:2008:gecco
%A Miikkulainen, Risto
%A Stanley, Kenneth O.
%B GECCO'08: Proc. 10th Genetic and Evolutionary Computation
Conf.
%C Atlanta, GA
%D 2008
%E Keijzer, Maarten
%E Antoniol, Giuliano
%E Bates Congdon, Clare
%E Deb, Kalyanmoy
%E Doerr, Benjamin
%E Hansen, Nikolaus
%E Holmes, John H.
%E Hornby, Gregory S.
%E Howard, Daniel
%E Kennedy, James
%E Kumar, Sanjeev
%E Lobo, Fernando G.
%E Miller, Julian Francis
%E Moore, Jason
%E Neumann, Frank
%E Pelikan, Martin
%E Pollack, Jordan
%E Sastry, Kumara
%E Stanley, Kenneth
%E Stoica, Adrian
%E Talbi, El-Ghazali
%E Wegener, Ingo
%I ACM Press
%K imported thesis
%P 2829--2848
%R 10.1145/1388969.1389080
%T Evolving Neural Networks
%X 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, we 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 game playing, robot control, resource optimization,
and cognitive science.
%@ 978-1-60558-130-9
@inproceedings{Miikkuklainen:2008:gecco,
abstract = {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, we 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 game playing, robot control, resource optimization,
and cognitive science.},
added-at = {2017-03-16T11:50:55.000+0100},
address = {Atlanta, GA},
author = {Miikkulainen, Risto and Stanley, Kenneth O.},
biburl = {https://www.bibsonomy.org/bibtex/2ceff89f732e40d5a40830bb7a6e5283f/krevelen},
booktitle = {GECCO'08: Proc. 10th Genetic and Evolutionary Computation
Conf.},
crossref = {gecco:2008},
doi = {10.1145/1388969.1389080},
editor = {Keijzer, Maarten and Antoniol, Giuliano and {Bates Congdon}, Clare and Deb, Kalyanmoy and Doerr, Benjamin and Hansen, Nikolaus and Holmes, John H. and Hornby, Gregory S. and Howard, Daniel and Kennedy, James and Kumar, Sanjeev and Lobo, Fernando G. and Miller, Julian Francis and Moore, Jason and Neumann, Frank and Pelikan, Martin and Pollack, Jordan and Sastry, Kumara and Stanley, Kenneth and Stoica, Adrian and Talbi, El-Ghazali and Wegener, Ingo},
interhash = {5ade24caa0a7934ab1f229df7afa2485},
intrahash = {ceff89f732e40d5a40830bb7a6e5283f},
isbn = {978-1-60558-130-9},
keywords = {imported thesis},
owner = {Rick},
pages = {2829--2848},
publisher = {ACM Press},
publisher_address = {New York},
timestamp = {2017-03-16T11:54:14.000+0100},
title = {Evolving Neural Networks},
year = 2008
}