Closed-Loop Learning of Visual Control Policies

Details Closed-Loop Learning of Visual Control Policies Closed-Loop Learning of Visual Control Policies

2011-10-10

arxiv.org/abs/1110.2210v1

Journal Of Artificial Intelligence Research, Volume 28, pages 349-391, 2007

Computer Science

Computer Vision and Pattern Recognition

Scientific paper

10.1613/jair.2110

In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-based image classifier in front of a reinforcement learning algorithm. The classifier partitions the visual space according to the presence or absence of few highly informative local descriptors that are incrementally selected in a sequence of attempts to remove perceptual aliasing. We also address the problem of fighting overfitting in such a greedy algorithm. Finally, we show how high-level visual features can be generated when the power of local descriptors is insufficient for completely disambiguating the aliased states. This is done by building a hierarchy of composite features that consist of recursive spatial combinations of visual features. We demonstrate the efficacy of our algorithms by solving three visual navigation tasks and a visual version of the classical Car on the Hill control problem.

Affiliated with

Also associated with

No associations

Rating

Closed-Loop Learning of Visual Control Policies does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Closed-Loop Learning of Visual Control Policies, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Closed-Loop Learning of Visual Control Policies will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-471076