Bridging the gap: Learning in the robocup simulation and midsize league

Bridging the gap: Learning in the robocup simulation and midsize league (2006)

Cached

Download Links

by Thomas Gabel , Sascha Lange , Martin Lauer , Martin Riedmiller

Venue:	In Proceedings of the 7th Portuguese Conference on Automatic Control (Controlo
Citations:	5 - 2 self

BibTeX

@INPROCEEDINGS{Gabel06bridgingthe,
    author = {Thomas Gabel and Sascha Lange and Martin Lauer and Martin Riedmiller},
    title = {Bridging the gap: Learning in the robocup simulation and midsize league},
    booktitle = {In Proceedings of the 7th Portuguese Conference on Automatic Control (Controlo},
    year = {2006}
}

Bookmark

OpenURL

Abstract

Abstract: In this paper, we discuss the application of reinforcement learning for autonomous robots using the RoboCup domain as benchmark. The paper compares successful learning approaches in simulation with learning on real robots and develops methodologies to overcome the additional problems in real world.

Citations

2827	Reinforcement Learning: An Introduction - Sutton, Barto - 1998
1060	Learning to predict by the methods of temporal differences - Sutton - 1988
484	Probabilistic Robotics - Thrun, Burgard, et al. - 2005
237	Multiagent reinforcement learning: theoretical framework and an algorithm - Hu, Wellman - 1998
169	On sequential simulation-based methods for Bayesian filtering - Doucet - 1998
37	Neural fitted Q iteration – first experiences with a data efficient neural reinforcement learning method - Riedmiller - 2005
25	Minoru Asada, Yasuo Kuniyoshi, Itsuki Noda, and Eiichi Osawa. RoboCup: The robot world cup initiative - Kitano - 1997
14	Using machine learning techniques in complex multi-agent domains - Riedmiller, Merke - 2003
2	A neural RL controller for speed control of a real robot. Submitted to: Robotics Science and Systems RSS06 - Hafner, Riedmiller - 2006
2	Sascha Lange and Martin Riedmiller (2005). Calculating the perfect match: an efficient and accurate approach for rob ot self-localization - Lauer
1	Gloye, Raúl Rojas and Mark Simon (2003). Predicting away robot control latency - Behnke, Egorova, et al.
1	Neural Networks for Pattern Classification - Bishop - 1995
1	Learning a partial behavior for a competetive robotic soccer agent. Künstliche Intelligenz - Gabel, Riedmiller - 2006
1	Brainstormers Tribots teamdescription. Submitted to: Robocup Symposium - Hafner, Lange, et al. - 2006
1	A plugin-based architecture for simulation - Kleiner, Buchheim - 2003
1	Vision based techniques of modeling the environment for an autonomous robot application. submitted to: International Journal of Computer Vision - Lauer, Lange - 2006
1	Sascha Lange and Martin Riedmiller (2006). Moton estimation of moving objects for autonomous mobile robots - Lauer
1	Fahrtplanung eines Roboters mithilfe von Reinforcement Learning. Master’s thesis - Müller - 2005