Accelerating Neuroevolutionary Methods Using a Kalman Filter
Editors: M. Keijzer
In Proceedings of the 10th Genetic and Evolutionary Computation Conference, (GECCO-2008), 12.7.-16.7.2008, Atlanta, Georgia, ACM, pages 1397-1404, 2008.
In recent years, neuroevolutionary methods have shown great promise in solving learning tasks, especially in domains that are stochastic, partially observable, and noisy. In this paper, we show how the Kalman filter can be exploited (1) to efficiently find an optimal solution (i. e. reducing the number of evaluations needed to find the solution), (2) to find solutions that are robust against noise, and (3) to recover or reconstruct missing state variables, traditionally known as state estimation in control engineering community. Our algorithm has been tested on the double pole balancing without velocities benchmark, and has achieved significantly better results on this benchmark than the published results of other algorithms to date.
Neuroevolution, Kalman Filter