Künstliche Intelligenz
3/09




KI Konferenz



KI Fachbereich

Böttcher IT Verlag

Heft 3/09

Schwerpunkt: Reinforcement Learning

Policy Search for Motor Primitives

Zusammenfassung:

Many motor skills in humanoid robotics can be learned using parametrized motor primitives from demonstrations. However, most interesting motor learning problems require self-improvement often beyond the reach of current reinforcement learning methods due to the high dimensionality of the state-space. We develop an EM-inspired algorithm applicable to complex motor learning tasks. We compare this algorithm to several well-known parametrized policy search methods and show that it outperforms them. We apply it to motor learning problems and show that it can learn the complex Ball-in-a-Cup task using a real Barrett WAM robot arm.

Autoren:

Jens Kober, Jan Peters

Seite/n:

38-40

Nummer:

3

Artikel als PDF

Back

 

Email: info(a)kuenstliche-intelligenz.de

©KI