Learning to drive a real car in 20 minutes
Autor(en): | Riedmiller, M. Montemerlo, M. Dahlkamp, H. |
Stichwörter: | Control laws; Data-driven; Q functions; Q values; Real robots; RL methods; Transition modeling, Education; Experiments; Information technology; Reinforcement; Reinforcement learning; Technology, Iterative methods | Erscheinungsdatum: | 2007 | Journal: | Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007 | Startseite: | 645 | Seitenende: | 650 | Zusammenfassung: | The paper describes our first experiments on Reinforcement Learning to steer a real robot car. The applied method, Neural Fitted Q Iteration (NFQ) is purely data-driven based on data directly collected from real-life experiments, i.e. no transition model and no simulation is used. The RL approach is based on learning a neural Q value function, which means that no prior selection of the structure of the control law is required. We demonstrate, that the controller is able to learn a steering task in less than 20 minutes directly on the real car. We consider this as an important step towards the competitive application of neural Q function based RL methods in real-life environments. © 2007 IEEE. |
Beschreibung: | Conference of Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007 ; Conference Date: 11 October 2007 Through 13 October 2007; Conference Code:72894 |
ISBN: | 9780769529998 | DOI: | 10.1109/FBIT.2007.37 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-49349084771&doi=10.1109%2fFBIT.2007.37&partnerID=40&md5=57de230f0032dc2092934d503b9d1edd |
Zur Langanzeige
Seitenaufrufe
1
Letzte Woche
0
0
Letzter Monat
0
0
geprüft am 17.05.2024