Publication
Learning complex motions by sequencing simpler motion templates
Gerhard Neumann; Wolfgang Maass; Jan Peters
In: Andrea Pohoreckyj Danyluk; Léon Bottou; Michael L. Littman (Hrsg.). Proceedings of the 26th Annual International Conference on Machine Learning. International Conference on Machine Learning (ICML-2009), June 14-18, Montreal, Quebec, Canada, Pages 753-760, ACM International Conference Proceeding Series, Vol. 382, ACM, 2009.
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.