Learning concurrent motor skills in versatile solution spaces

Future robots need to autonomously acquire motor skills in order to reduce their reliance on human programming. Many motor skill learning methods concentrate on learning a single solution for a given task. However, discarding information about additional solutions during learning unnecessarily limits autonomy. Such favoring of single solutions often requires re-learning of motor skills when the task, the environment or the robot's body changes in a way that renders the learned solution infeasible. Future robots need to be able to adapt to such changes and, ideally, have a large repertoire of movements to cope with such problems. In contrast to current methods, our approach simultaneously learns multiple distinct solutions for the same task, such that a partial degeneration of this solution space does not prevent the successful completion of the task. In this paper, we present a complete framework that is capable of learning different solution strategies for a real robot Tetherball task.

Authors

• Christian G. Daniel
• Gerhard Neumann
• Jan Peters 0001

Keywords

• Robots
• Entropy
• Games
• Equations
• Monte Carlo methods
• Optimization
• Mathematical model
• Motor Skills
• Solution Space
• Multiple Solutions
• Real Robot
• Optimization Problem
• Search Algorithm
• Learning Curve
• Lagrange Multiplier
• Kullback-Leibler
• Motor Task
• Reward Function
• Markov Decision Process
• Hierarchical Framework
• Hierarchical Representation
• Learning Trials
• Table Tennis
• Linear Dynamical System
• Task Solution
• Single Gaussian
• Robot Learning
• Policy Search
• Ball Speed
• Games For Children
• Learning Setup