go back

Reinforcement learning on complex visual stimuli

Niko Wilbert, Robert Legenstein, Mathias Franzius, Laurenz Wiskott, "Reinforcement learning on complex visual stimuli", BMC Neuroscience, vol. 10, no. Suppl 1, pp. P90, 2009.

Abstract

Animals are confronted with the problem of initiating motor actions based on very complex sensor y input. We have build a biologically plausible model that uses reinforcement learning on complex visual stimuli to direct an agent towards a target. This is made possible by first extracting a high-level representation of the scene with a hierarchical network and then applying a correlation based reinforcement learning rule.



Download Bibtex file Download PDF

Search