Learning to select primitives and generate sub-goals from practice

This paper focuses on learning to select behavioral primitives and generate sub-goals from practicing a task. We present a novel algorithm that combines Q-learning and a locally weighted learning method to improve primitive selection and sub-goal generation. We demonstrate this approach applied to the tilt maze task. Our robot initially learns to perform this task using learning from observation, and then learns from practice.

[1]  Gordon Cheng,et al.  Humanoid robot learning and game playing using PC-based vision , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  R. Magill.  Motor Learning And Control , 1980 .

[3]  Stefan Schaal,et al.  Statistical Learning for Humanoid Robots , 2002, Auton. Robots.

[4]  Maja J. Mataric,et al.  Automated Derivation of Primitives for Movement Classification , 2000, Auton. Robots.

[5]  Andrew G. Barto,et al.  Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density , 2001, ICML.

[6]  Stefan Schaal,et al.  Scalable Techniques from Nonparametric Statistics for Real Time Robot Learning , 2002, Applied Intelligence.

[7]  Christopher G. Atkeson,et al.  A Framework for Learning from Observation Using Primitives , 2002, RoboCup.

[8]  W. Shebilske,et al.  Motor Learning and Control , 1993 .

[9]  Maja J. Matarić,et al.  Behavior-based primitives for articulated control , 1998 .

[10]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[11]  Ronald C. Arkin,et al.  An Behavior-based Robotics , 1998 .

[12]  Avinash C. Kak,et al.  Automatic learning of assembly tasks using a DataGlove system , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[13]  Masayuki Inaba,et al.  Learning by watching: extracting reusable task knowledge from visual observation of human performance , 1994, IEEE Trans. Robotics Autom..

[14]  Christopher G. Atkeson,et al.  Learning from observation using primitives , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[15]  Stefan Schaal,et al.  Locally Weighted Projection Regression : An O(n) Algorithm for Incremental Real Time Learning in High Dimensional Space , 2000 .