Application of Q-Learning in Robot Grasping Tasks

Wengerek T, Ritter H (1993)
In: ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993. Gielen S, Kappen B (Eds);London: Springer: 268-273.

Conference Paper | Published | English

No fulltext has been uploaded

Author
;
Editor
Gielen, S. ; Kappen, B.
Abstract
Reinforcement learning plays a major part in the adaptive behaviour of autonomous robots. But in real-world environments reinforcement learning techniques, like Q-learning, meet great difficulties because of rapidly growing search spaces. We explored the characteristics of discrete Q-learning in a high-dimensional continuous setup consisting of a simulated robot grasping task. Very simple sensors in this setup allow only a rather coarse identification of the actual “physical” state, thus leading to consequences known as “perceptual aliasing”. We identified parameters — especially the sensory sampling-rate — directly controlling the grade of generality of the policies to be learned. Actually in case of the more general policies performing the raw positioning effects of ambiguity can be suppressed. So the system can find feasible grasping positions after few explorative actions and we suggest, that a neural net supporting Q-learning could improve the overall performance significantly.
Publishing Year
Conference
IJCNN '93
Location
Amsterdam
Conference Date
1993-09-13 – 1993-09-16
PUB-ID

Cite this

Wengerek T, Ritter H. Application of Q-Learning in Robot Grasping Tasks. In: Gielen S, Kappen B, eds. ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993. London: Springer; 1993: 268-273.
Wengerek, T., & Ritter, H. (1993). Application of Q-Learning in Robot Grasping Tasks. In S. Gielen & B. Kappen (Eds.), ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993 (pp. 268-273). London: Springer.
Wengerek, T., and Ritter, H. (1993). “Application of Q-Learning in Robot Grasping Tasks” in ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993, ed. S. Gielen and B. Kappen (London: Springer), 268-273.
Wengerek, T., & Ritter, H., 1993. Application of Q-Learning in Robot Grasping Tasks. In S. Gielen & B. Kappen, eds. ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993. London: Springer, pp. 268-273.
T. Wengerek and H. Ritter, “Application of Q-Learning in Robot Grasping Tasks”, ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993, S. Gielen and B. Kappen, eds., London: Springer, 1993, pp.268-273.
Wengerek, T., Ritter, H.: Application of Q-Learning in Robot Grasping Tasks. In: Gielen, S. and Kappen, B. (eds.) ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993. p. 268-273. Springer, London (1993).
Wengerek, Thomas, and Ritter, Helge. “Application of Q-Learning in Robot Grasping Tasks”. ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993. Ed. S. Gielen and B. Kappen. London: Springer, 1993. 268-273.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar
ISBN Search