Empirical Inference
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.
| Author(s): | Peters, J. and Kober, J. |
| Links: | |
| Journal: | KI - Zeitschrift K{\"u}nstliche Intelligenz |
| Volume: | 23 |
| Number (issue): | 3 |
| Pages: | 38-40 |
| Year: | 2009 |
| Month: | August |
| Day: | 0 |
| BibTeX Type: | Article (article) |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
BibTeX
@article{6871,
title = {Policy Search for Motor Primitives},
journal = {KI - Zeitschrift K{\"u}nstliche Intelligenz},
abstract = {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.},
volume = {23},
number = {3},
pages = {38-40},
organization = {Max-Planck-Gesellschaft},
school = {Biologische Kybernetik},
month = aug,
year = {2009},
author = {Peters, J. and Kober, J.},
month_numeric = {8}
}