EANT+KALMAN: An Efficient Reinforcement Learning Method for Continuous State Partially Observable Domains

Yohannes Kassahun, José de Gea Fernández, Jan Hendrik Metzen, Mark Edgington, Frank Kirchner

In: Andreas Dengel , K. Berns , Thomas Breuel , Frank Bomarius , Thomas Roth-Berghofer (Hrsg.). KI 2008: Advances in Artificial Intelligence. German Conference on Artificial Intelligence (KI-08) 31st September 23-26 Kaiserslautern Germany Seiten 241-248 Lecture Notes in Artificial Intelligence (LNAI) 5243 Springer Berlin/ Heidelberg 2008.


In this contribution we present an extension of a neuroevolutionary method called Evolutionary Acquisition of Neural Topologies (EANT) [11] that allows the evolution of solutions taking the form of a POMDP agent (Partially Observable Markov Decision Process) [8]. The solution we propose involves cascading a Kalman filter [10] (state estimator) and a feed-forward neural network. The extension (EANT+KALMAN) has been tested on the double pole balancing without velocity benchmark, achieving significantly better results than the to date published results of other algorithms.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence