Abstract
Although Reinforcement Learning methods have meanwhile been successfully applied to a wide range of different application scenarios, there is still a lack of methods that would allow the direct application of reinforcement learning to real systems. The key capability of such learning systems is the efficency with respect to the number of interactions with the real system. Several examples are given that illustrate recent progress made in that direction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Schoknecht, R., Riedmiller Using, M.: reinforcement learning for engine control. In: Proc. of ICANN 1999 (1999)
Riedmiller, M.: Concepts and facilities of a neural reinforcement learning control architecture for technical process control. Journal of Neural Computing and Application (2000)
Riedmiller, M., Merke, A.: Using Machine Learning Techniques in Complex Multi- Agent Domains. In: Stamatescu, I., Menzel, W., Richter, M., Ratsch, U. (eds.) Perspectives on Adaptivity and Learning. LNCS, Springer, Heidelberg (2002)
Lauer, M., Riedmiller, M.: Generalisation in Reinforcement Learning and the Use of Observation-Based Learning. In: Kokai, G., Zeidler, J. (eds.) Proc. of the FGML Workshop (2002)
Schoknecht, R., Riedmiller, M.: Learning to Control at Multiple Time Scales. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714, Springer, Heidelberg (2003)
Hafner, R., Riedmiller, M.: Reinforcement Learning on an omnidirectional mobile robot. In: Proc. IROS 2003 (2003)
Barto, A.G., Crites, R.H.: Improving Elevator Performance using Reinforcement Learning. In: Proc. NIPS 1996 (1996)
Mahadevan, S., Theocharous, G.: Optimization production manufacturing using reinforcement learning. In: Proc. FLAIRS 1998 (1998)
Barto, A.G., Bradtke, S.J., Singh, S.P.: Learning to Act using Real-Time Dynamic Programming. Artificial Intelligence 72 (1995)
Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press, Cambridge (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Riedmiller, M. (2004). Machine Learning for Autonomous Robots. In: Biundo, S., Frühwirth, T., Palm, G. (eds) KI 2004: Advances in Artificial Intelligence. KI 2004. Lecture Notes in Computer Science(), vol 3238. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30221-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-30221-6_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23166-0
Online ISBN: 978-3-540-30221-6
eBook Packages: Springer Book Archive