Using reward-weighted imitation for robot Reinforcement Learning

Peters, J; Kober, J

doi:10.1109/ADPRL.2009.4927549

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Conference Paper

Using reward-weighted imitation for robot Reinforcement Learning

MPS-Authors

/persons/resource/persons84135

Peters, J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84021

Kober, J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4927549
(Publisher version)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Peters, J., & Kober, J. (2009). Using reward-weighted imitation for robot Reinforcement Learning. In 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (pp. 226-232). Piscataway, NJ, USA: IEEE Service Center.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-C505-6

Abstract

Reinforcement Learning is an essential ability for robots to learn new motor skills. Nevertheless, few methods scale into the domain of anthropomorphic robotics. In order to improve in terms of efficiency, the problem is reduced onto reward-weighted imitation. By doing so, we are able to generate a framework for policy learning which both unifies previous reinforcement learning approaches and allows the derivation of novel algorithms. We show our two most relevant applications both for motor primitive learning (e.g., a complex Ball-in-a-Cup task using a real Barrett WAM robot arm) and learning task-space control.