Learning complex motions by sequencing simpler motion templates

Neumann, Gerhard, Maass, W. and Peters, J. (2009) Learning complex motions by sequencing simpler motion templates. In: 26th Annual International Conference on Machine Learning (ICML 2009), 14-18 June 2009, Montreal, QC; Canada.

Documents
ICML2009-Neumann_[0].pdf
[img]
[Download]
[img] PDF
ICML2009-Neumann_[0].pdf - Whole Document

776B
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Abstraction of complex, longer motor tasks into simpler elemental movements enables humans and animals to exhibit motor skills which have not yet been matched by robots. Humans intuitively decompose complex motions into smaller, simpler segments. For example when describing simple movements like drawing a triangle with a pen, we can easily name the basic steps of this movement.

Surprisingly, such abstractions have rarely been used in artificial motor skill learning algorithms. These algorithms typically choose a new action (such as a torque or a force) at a very fast time-scale. As a result, both policy and temporal credit assignment problem become unnecessarily complex - often beyond the reach of current machine learning methods.

We introduce a new framework for temporal abstractions in reinforcement learning (RL), i.e. RL with motion templates. We present a new algorithm for this framework which can learn high-quality policies by making only few abstract decisions.

Keywords:Reinfrocement Learning, Movement Primitives, Sequencing, complex motion, machine learning methods
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:25795
Deposited On:24 Feb 2017 10:06

Repository Staff Only: item control page