Peters, Jan and Schaal, Stefan (2004) Learning Motor Primitives with Reinforcement Learning. In: 11th Joint Symposium on Neural Computation, 15 May 2004, University of Southern California. (Unpublished) http://resolver.caltech.edu/CaltechJSNC:2004.poster020
Full text not available from this repository.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechJSNC:2004.poster020
One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients . We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion.
|Item Type:||Conference or Workshop Item (Poster)|
|Additional Information:||Poster to be added|
|Usage Policy:||You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format|
|Deposited By:||Imported from CaltechJSNC|
|Deposited On:||08 Jul 2004|
|Last Modified:||24 Oct 2011 21:36|
Repository Staff Only: item control page