Most optimization algorithms must undergo time consuming parameter adaptation in order to optimally solve complex, real-world control tasks. Parameter adaptation is inherently a bilevel optimization problem where the lower level objective function is the performance of the control parameters discovered by an optimization algorithm and the upper level objective function is the performance of the algorithm given its parametrization. In this paper, a novel method called MetaEvolutionary Algorithm (MEA) is presented and shown to be capable of efficiently discovering optimal parameters for neuroevolution to solve control problems. In two challenging examples, double pole balancing and helicopter hovering, MEA discovers optimized parameters that result in better performance than hand tuning and other automatic methods. Bilevel optimization in general and MEA in particular, is thus a promising approach for solving difficult control tasks.

PDF

In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2015), 871–878, Madrid, Spain, July 2015.

@inproceedings{liang:gecco15, title={Evolutionary Bilevel Optimization for Complex Control Tasks}, author={Jason Zhi Liang and Risto Miikkulainen}, booktitle={Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2015)}, month={July}, address={Madrid, Spain}, pages={871–878}, url="http://nn.cs.utexas.edu/?liang:gecco15", year={2015} }