Intrinsically motivated hierarchical manipulation

— We present a framework for the programming of manipulation behavior by means of an intrinsic reward function that encourages the building of deep control knowledge. We show how this framework can be used to teach new manipulation skills in a hierarchical and incremental fashion. We demonstrate the contributions of this paper on a humanoid robot through three incremental learning stages.

• Type: Conference
• Year: 2008
• Where: ICRA
• Authors: Stephen Hart, Shijaj Sen, Roderic A. Grupen
• Keywords: Deep Control Knowledge, ICRA 2008, Incremental Learning Stages, Intrinsic Reward Function, Robotics