• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Transfer via Inter-Task Mappings in Policy Search Reinforcement Learning.
Matthew
E. Taylor, Shimon Whiteson, and Peter
Stone.
In The Sixth International Joint Conference on Autonomous Agents and Multiagent Systems, May 2007.
AAMAS-2007
[PDF]222.5kB [postscript]525.2kB
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 (\sc 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 \sc tvitm-ps can markedly reduce learning time when full inter-task mappings are available. The results also demonstrate that \sc 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.
@InProceedings{AAMAS07-taylor,
author="Matthew E.\ Taylor and Shimon Whiteson and Peter Stone",
title="Transfer via Inter-Task Mappings in Policy Search Reinforcement Learning",
booktitle="The Sixth International Joint Conference on Autonomous Agents and Multiagent Systems",
month="May",year="2007",
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 ({\sc 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 {\sc tvitm-ps} can markedly reduce learning time
when full inter-task mappings are available. The
results also demonstrate that {\sc tvitm-ps} still
succeeds when given only incomplete inter-task
mappings. Furthermore, we present a novel method for
\emph{learning} such mappings when they are not
available, and give results showing they perform
comparably to hand-coded mappings. },
wwwnote={<a href="http://www.aamas2007.nl/">AAMAS-2007</a>},
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 17, 2024 18:42:55