Reinforcement learning with raw image pixels as input state

Authors:
Damien Ernst;Raphaël Marée;Louis Wehenkel
Affiliations:
Department of Electrical Engineering and Computer Science, Institut Montefiore – University of Liège, Liège, Belgium;Department of Electrical Engineering and Computer Science, Institut Montefiore – University of Liège, Liège, Belgium;Department of Electrical Engineering and Computer Science, Institut Montefiore – University of Liège, Liège, Belgium
Venue:
IWICPAS'06 Proceedings of the 2006 Advances in Machine Vision, Image Processing, and Pattern Analysis international conference on Intelligent Computing in Pattern Analysis/Synthesis
Year:
2006

Citing 4
Cited 1

Random Subwindows for Robust Image Classification

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Tree-Based Batch Mode Reinforcement Learning

The Journal of Machine Learning Research
Interactive learning of mappings from visual percepts to actions

ICML '05 Proceedings of the 22nd international conference on Machine learning
Extremely randomized trees

Machine Learning

Reinforcement learning versus model predictive control: a comparison on a power system problem

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.