Policy Gradient Methods for Robotics

Citations Over TimeTop 1% of 2006 papers

Abstract

The acquisition and improvement of motor skills and control policies for robotics from trial and error is of essential importance if robots should ever leave precisely pre-structured environments. However, to date only few existing reinforcement learning methods have been scaled into the domains of high-dimensional robots such as manipulator, legged or humanoid robots. Policy gradient methods remain one of the few exceptions and have found a variety of applications. Nevertheless, the application of such methods is not without peril if done in an uninformed manner. In this paper, we give an overview on learning with policy gradient methods for robotics with a strong focus on recent advances in the field. We outline previous applications to robotics and show how the most recently developed methods can significantly improve learning performance. Finally, we evaluate our most promising algorithm in the application of hitting a baseball with an anthropomorphic arm

Related Papers

• → The Tele-operation of the Humanoid Robot-Whole Body Operation for Humanoid Robots in Contact with Environment-(2006)11 cited
• Humanoid robotics(2007)
• → Humanoid robotics(2007)4 cited
• → Experimental evaluation of the dynamic simulation of biped walking of humanoid robots(2004)27 cited
• → G1500-3-3 Passing through a door by a humanoid robot : Experimental verification(2010)2 cited