[en] We report in this paper some positive simulation results obtained when image pixels are directly used as input state of a reinforcement learning algorithm. The reinforcement learning algorithm chosen to carry out the simulation is a batch-mode algorithm known as fitted Q iteration.
Disciplines :
Computer science
Author, co-author :
Ernst, Damien ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Marée, Raphaël ; Université de Liège - ULiège > Systèmes et modélisation
Wehenkel, Louis ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
Reinforcement learning with raw image pixels as input state
Publication date :
2006
Event name :
International Workshop on Intelligent Computing in Pattern Analysis/Synthesis (IWICPAS)
Event place :
Xi'an, China
Event date :
August 26-27, 2006
Audience :
International
Main work title :
Advances in machine vision, image processing & pattern analysis (Lecture notes in computer science, Vol. 4153)
D. Ernst, P. Geurts, and L. Wehenkel, Tree-based batch mode reinforcement learning. Journal of Machine Learning Research, 6:503-556, April 2005.
P. Geurts, D. Ernst, and L. Wehenkel. Extremely randomized trees. Machine Learning, 36(1):3-42, 2006.
S. Jodogne and S. Piater. Interactive learning of mappings from visual percepts to actions. In L. De Raedt and S. Wrobel, editors, Proceedings of the 22nd International Conference on Machine Learning, pages 393-400, August 2005.
M. Lagoudakis and R. Parr. Reinforcement learning as classification: leveraging modern classifiers. In T. Faucett and N. Mishra, editors, Proceedings of 20th International Conference on Machine Learning, pages 424-431, 2003.
R. Marée, P. Geurts, J. Piater, and L. Wehenkel. Random subwindows for robust image classification. In C. Schmid, S. Soatto, and C. Tomasi, editors, Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, volume 1, pages 34-40. IEEE, June 2005.
