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.

Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Konferenzbeitrag | Veröffentlicht | Englisch
Autor
;
Herausgeber
;
Abstract / Bemerkung
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.
Erscheinungsjahr
Titel des Konferenzbandes
ICANN 93. Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993
Seite
268-273
Konferenz
IJCNN '93
Konferenzort
Amsterdam
Konferenzdatum
1993-09-13 – 1993-09-16
PUB-ID

Zitieren

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. doi:10.1007/978-1-4471-2063-6_62
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, Gielen, S., and Kappen, B. eds. (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.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche