Sciweavers

ECML
2006
Springer

Approximate Policy Iteration for Closed-Loop Learning of Visual Tasks

14 years 1 months ago
Approximate Policy Iteration for Closed-Loop Learning of Visual Tasks
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for the closed-loop learning of mappings from images to actions. This approach requires a family of function approximators that maps visual percepts to a real-valued function. For this purpose, we use Regression Extra-Trees, a fast, yet accurate and versatile machine learning algorithm. The inputs of the Extra-Trees consist of a set of visual features that digest the informative patterns in the visual signal. We also show how to parallelize the Extra-Tree learning process to further reduce the computational expense, which is often essential in visual tasks. Experimental results on real-world images are given that indicate that the combination of API with Extra-Trees is a promising framework for the interactive learning of visual tasks.
Sébastien Jodogne, Cyril Briquet, Justus H.
Added 22 Aug 2010
Updated 22 Aug 2010
Type Conference
Year 2006
Where ECML
Authors Sébastien Jodogne, Cyril Briquet, Justus H. Piater
Comments (0)