Transfer via inter-task mappings in policy search reinforcement learning. (2007)
| Venue: | In Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, |
| Citations: | 42 - 19 self |
BibTeX
@INPROCEEDINGS{Taylor07transfervia,
author = {Matthew E Taylor and Shimon Whiteson and Peter Stone},
title = {Transfer via inter-task mappings in policy search reinforcement learning.},
booktitle = {In Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems,},
year = {2007},
pages = {37}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
ABSTRACT The ambitious goal of transfer learning is to accelerate learning on a target task after training on a different, but related, source task. While many past transfer methods have focused on transferring value-functions, this paper presents a method for transferring policies across tasks with different state and action spaces. In particular, this paper utilizes transfer via inter-task mappings for policy search methods (TVITM-PS) to construct a transfer functional that translates a population of neural network policies trained via policy search from a source task to a target task. Empirical results in robot soccer Keepaway and Server Job Scheduling show that TVITM-PS can markedly reduce learning time when full inter-task mappings are available. The results also demonstrate that TVITM-PS still succeeds when given only incomplete inter-task mappings. Furthermore, we present a novel method for learning such mappings when they are not available, and give results showing they perform comparably to hand-coded mappings.
