neural networks research group
areas
people
projects
demos
publications
software/data
Eugenic Neuro-Evolution For Reinforcement Learning (2000)
Daniel Polani
and
Risto Miikkulainen
In this paper we introduce EuSANE, a novel reinforcement learning algorithm based on the SANE neuro-evolution method. It uses a global search algorithm, the Eugenic Algorithm, to optimize the selection of neurons to the hidden layer of SANE networks. The performance of EuSANE is evaluated in the two-pole balancing benchmark task. EuSANE is several times faster than SANE in this task, showing that it is a highly efficient method of reinforcement learning in challenging domains.
View:
PDF
,
PS
Citation:
In
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2000)
, 1041-1046, San Francisco, 2000. Morgan Kaufmann.
Bibtex:
@InProceedings{polani:gecco00, title={Eugenic Neuro-Evolution For Reinforcement Learning}, author={Daniel Polani and Risto Miikkulainen}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2000)}, address={San Francisco}, publisher={Morgan Kaufmann}, pages={1041-1046}, url="http://nn.cs.utexas.edu/?polani:gecco00", year={2000} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Daniel Polani
Postdoctoral Alumni
d polani [at] herts ac uk
Projects
Eugenic Evolution: The EuA, EuSANE, and TEAM
1998 - 2002
Areas of Interest
Evolutionary Computation
Neuroevolution
Reinforcement Learning