Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Multi-agent inverse reinforcement learning

 
: Natarajan, S.; Kunapuli, G.; Judah, K.; Tadepalli, P.; Kersting, K.; Shavlik, J.

:

Draghici, S. ; IEEE Computer Society; Institute of Electrical and Electronics Engineers -IEEE-:
Ninth International Conference on Machine Learning and Applications, ICMLA 2010 : Washington, DC, 12 - 14 December 2010
Piscataway: IEEE, 2010
ISBN: 978-0-7695-4300-0
ISBN: 978-1-4244-9211-4
S.395-400
International Conference on Machine Learning and Applications (ICMLA) <9, 2010, Washington>
Englisch
Konferenzbeitrag
Fraunhofer IAIS ()

Abstract
Learning the reward function of an agent by observing its behavior is termed inverse reinforcement learning and has applications in learning from demonstration or apprenticeship learning. We introduce the problem of multi-agent inverse reinforcement learning, where reward functions of multiple agents are learned by observing their uncoordinated behavior. A centralized controller then learns to coordinate their behavior by optimizing a weighted sum of reward functions of all the agents. We evaluate our approach on a traffic-routing domain, in which a controller coordinates actions of multiple traffic signals to regulate traffic density. We show that the learner is not only able to match but even significantly outperform the expert.

: http://publica.fraunhofer.de/dokumente/N-188493.html