papers AI Learner
The Github is limit! Click to go to the new site.

Learning Manipulation Skills Via Hierarchical Spatial Attention

2019-04-19
Marcus Gualtieri, Robert Platt

Abstract

Learning generalizable skills in robotic manipulation has long been challenging due to real-world sized observation and action spaces. One method for addressing this problem is attention focus – the robot learns where to attend its sensors and irrelevant details are ignored. However, these methods have largely not caught on due to the difficulty of learning a good attention policy and the added partial observability induced by a narrowed window of focus. This article addresses the first issue by constraining gazes to a spatial hierarchy. For the second issue, we identify a case where the partial observability induced by attention does not prevent Q-learning from finding an optimal policy. We conclude with real-robot experiments on challenging pick-place tasks demonstrating the applicability of the approach.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.09191

PDF

http://arxiv.org/pdf/1904.09191


Similar Posts

Comments