An Integrated Connectionist Approach to Reinforcement Learning for Robotic Control: The Advantages of Indexed Partitioning (2000)
| Venue: | In Proceedings of the Seventeenth International Conf. on Machine Learning |
| Citations: | 3 - 0 self |
BibTeX
@INPROCEEDINGS{Hougen00anintegrated,
author = {Dean Hougen Hougen and Maria Gini and James Slagle},
title = {An Integrated Connectionist Approach to Reinforcement Learning for Robotic Control: The Advantages of Indexed Partitioning},
booktitle = {In Proceedings of the Seventeenth International Conf. on Machine Learning},
year = {2000},
publisher = {Morgan Kaufmann}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We explore the use of a connectionistlearning system designed to allow the application of reinforcement learning to robot control. In particular, we compare direct and indexed partitioning methods and find indexed partitioning has advantages in time and space complexity, learning speed (measured in trials) , and success rate. We make these comparisons based on extensive simulations and runs on a real robot learning on-line. 1.
