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.

PDF, PS

In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2000), 1041-1046, San Francisco, 2000. Morgan Kaufmann.

@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} }