Learning sequential motor tasks

Many real robot applications require the sequential use of multiple distinct motor primitives. This requirement implies the need to learn the individual primitives as well as a strategy to select the primitives sequentially. Such hierarchical learning problems are commonly either treated as one complex monolithic problem which is hard to learn, or as separate tasks learned in isolation. However, there exists a strong link between the robots strategy and its motor primitives. Consequently, a consistent framework is needed that can learn jointly on the level of the individual primitives and the robots strategy. We present a hierarchical learning method which improves individual motor primitives and, simultaneously, learns how to combine these motor primitives sequentially to solve complex motor tasks. We evaluate our method on the game of robot hockey, which is both difficult to learn in terms of the required motor primitives as well as its strategic elements.

Authors

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

Keywords

• Robots
• Vectors
• Entropy
• Optimization
• Games
• Search methods
• Sequential analysis
• Motor Task
• Motor Sequence Task
• Real Robot
• Complex Motor Tasks
• Optimization Problem
• Feature Representation
• Parametrized
• Parameter Vector
• Target Area
• Shape Parameter
• Stationary Distribution
• Kullback-Leibler
• Robotic Arm
• Multiple Solutions
• Reward Function
• Markov Decision Process
• Sequence Learning
• Policy Learning
• Redistributive Policies
• Single Decision
• Policy Search
• Beginning Of Episode
• Average Reward
• State Terms
• Motor Skills