Abstract
The challenging task of autonomously learning skills without the help of a teacher, solely based on feedback from the environment to actions, is called reinforcement learning. Still being an active area of research, some impressive results can be shown on robots. Reinforcement learning enables robots to learn motor skills as well as simple cognitive behavior. We use a simple robot with only two degrees of freedom to demonstrate the strengths of the value iteration and Q-learning algorithms, as well as their limitations.
Notes
- 1.
The arm movement space consisting of arcs is rendered as a right-angled grid.
- 2.
Further information and related sources about crawling robots are available through www.hs-weingarten.de/~ertel/kibuch.
References
A. Billard, S. Calinon, R. Dillmann, and S. Schaal. Robot programming by demonstration. In B. Siciliano and O. Khatib, editors, Handbook of Robotics, pages 1371–1394. Springer, Berlin, 2008.
R. E. Bellman. Dynamic Programming. Princeton University Press, Princeton, 1957.
A. G. Barto and S. Mahadevan. Recent advances in hierarchical reinforcement learning. Discrete Event Syst., Special Issue on Reinforcement Learning, 13:41–77, 2003.
W. Ertel, M. Schneider, R. Cubek, and M. Tokic. The teaching-box: a universal robot learning framework. In Proceedings of the 14th International Conference on Advanced Robotics (ICAR 2009), 2009. www.servicerobotik.hs-weingarten.de/teachingbox.
L. P. Kaelbling, M. L. Littman, and A. P. Moore. Reinforcement learning: a survey. J. Artif. Intell. Res., 4:237–285, 1996. www-2.cs.cmu.edu/afs/cs/project/jair/pub/volume4/kaelbling96a.pdf.
H. Kimura, K. Miyazaki, and S. Kobayashi. Reinforcement learning in POMDPs with function approximation. In 14th International Conference on Machine Learning, pages 152–160. Morgan Kaufmann, San Mateo, 1997. http://sysplan.nams.kyushu-u.ac.jp/gen/papers/JavaDemoML97/robodemo.html.
T. Mitchell. Machine Learning. McGraw–Hill, New York, 1997. www-2.cs.cmu.edu/~tom/mlbook.html.
L. Panait and S. Luke. Cooperative multi-agent learning: the state of the art. Auton. Agents Multi-Agent Syst., 11(3):387–434, 2005.
J. Peters and S. Schaal. Reinforcement learning of motor skills with policy gradients. Neural Netw., 21(4):682–697, 2008. http://www-clmc.usc.edu/publications/P/peters-NN2008.pdf.
M. Riedmiller, M. Montemerlo, and H. Dahlkamp. Learning to drive a real car in 20 minutes. In FBIT ’07: Proceedings of the 2007 Frontiers in the Convergence of Bioscience and Information Technologies, pages 645–650. IEEE Computer Society, Washington, DC, 2007.
The robocup soccer simulator. http://sserver.sourceforge.net.
R. Sutton and A. Barto. Reinforcement Learning. MIT Press, Cambridge, 1998. www.cs.ualberta.ca/~sutton/book/the-book.html.
M. Schneider and W. Ertel. Robot learning by demonstration with local gaussian process regression. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’10), 2010.
P. Stone, R. S. Sutton, and G. Kuhlmann. Reinforcement learning for robocup-soccer keepaway. Adaptive Behavior, 2005. www.cs.utexas.edu/~pstone/Papers/bib2html-links/AB05.pdf.
C. Szepesvari. Algorithms for Reinforcement Learning. Morgan & Claypool, San Rafael, 2010. Draft available online: http://www.ualberta.ca/~szepesva/RLBook.html.
R. Tedrake. Learning control at intermediate Reynolds numbers. In Workshop on: Robotics Challenges for Machine Learning II, International Conference on Intelligent Robots and Systems (IROS 2008), Nice, France, 2008.
M. Tokic, W. Ertel, and J. Fessler. The crawler, a class room demonstrator for reinforcement learning. In Proceedings of the 22nd International Florida Artificial Intelligence Research Society Conference (FLAIRS 09). AAAI Press, Menlo Park, 2009.
G. Tesauro. Temporal difference learning and td-gammon. Commun. ACM, 38(3), 1995. www.research.ibm.com/massive/tdl.html.
M. Tokic. Entwicklung eines Lernfähigen Laufroboters. Diplomarbeit Hochschule Ravensburg-Weingarten, 2006. Inklusive Simulationssoftware verfügbar auf www.hs-weingarten.de/~ertel/kibuch.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Springer-Verlag London Limited
About this chapter
Cite this chapter
Ertel, W. (2011). Reinforcement Learning. In: Introduction to Artificial Intelligence. Undergraduate Topics in Computer Science. Springer, London. https://doi.org/10.1007/978-0-85729-299-5_10
Download citation
DOI: https://doi.org/10.1007/978-0-85729-299-5_10
Publisher Name: Springer, London
Print ISBN: 978-0-85729-298-8
Online ISBN: 978-0-85729-299-5
eBook Packages: Computer ScienceComputer Science (R0)