Eugenic Neuro-Evolution For Reinforcement Learning (2000)
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), pp. 1041-1046, San Francisco 2000. Morgan Kaufmann.
Bibtex:

Risto Miikkulainen Faculty risto [at] cs utexas edu
Daniel Polani Postdoctoral Alumni d polani [at] herts ac uk