Publica
Hier finden Sie wissenschaftliche Publikationen aus den FraunhoferInstituten. Leveraging Domain Knowledge for Reinforcement Learning using MMC Architectures
 Tetko, I.V.: Artificial Neural Networks and Machine Learning  ICANN 2019. Deep Learning : 28th International Conference on Artificial Neural Networks, Munich, Germany, September 1719, 2019, Proceedings, Part II Cham: Springer International Publishing, 2019 (Lecture Notes in Computer Science 11728) ISBN: 9783030304836 (Print) ISBN: 9783030304843 (Online) pp.595607 
 International Conference on Artificial Neural Networks (ICANN) <28, 2019, Munich> 

 English 
 Conference Paper 
 Fraunhofer IAIS () 
Abstract
Despite the success of reinforcement learning methods in various simulated robotic applications, endtoend training suffers from extensive training times due to high sample complexity and does not scale well to realistic systems. In this work, we speed up reinforcement learning by incorporating domain knowledge into policy learning. We revisit an architecture based on the mean of multiple computations (MMC) principle known from computational biology and adapt it to solve a reacher task. We approximate the policy using a simple MMC network, experimentally compare this idea to endtoend deep learning architectures, and show that our approach reduces the number of interactions required to approximate a suitable policy by a factor of ten.