Matthew E. Taylor's Publications

Sorted by DateClassified by Publication TypeSorted by First Author Last NameClassified by Research Category

Transfer Learning via Inter-Task Mappings for Temporal Difference Learning

Matthew E. Taylor, Peter Stone, and Yaxin Liu. Transfer Learning via Inter-Task Mappings for Temporal Difference Learning. Journal of Machine Learning Research, 8(1):2125–2167, 2007.

Download

[PDF]499.9kB  [postscript]831.3kB  

Abstract

Temporal difference (TD) learning has become a popular reinforcement learning technique in recent years. TD methods, relying on function approximators to generalize learning to novel situations, have had some experimental successes and have been shown to exhibit some desirable properties in theory, but the most basic algorithms have often been found slow in practice. This empirical result has motivated the development of many methods that speed up reinforcement learning by modifying a task for the learner or helping the learner better generalize to novel situations. This article focuses on generalizing across tasks, thereby speeding up learning, via a novel form of transfer using handcoded task relationships. We compare learning on a complex task with three function approximators, a cerebellar model arithmetic computer (CMAC), an artificial neural network (ANN), and a radial basis function (RBF), and empirically demonstrate that directly transferring the action-value function can lead to a dramatic speedup in learning with all three. Using transfer via inter-task mapping (tvitm), agents are able to learn one task and then markedly reduce the time it takes to learn a more complex task. Our algorithms are fully implemented and tested in the RoboCup soccer Keepaway domain.

BibTeX Entry

@Article{JMLR07-taylor,
	Author="Matthew E.\ Taylor and Peter Stone and Yaxin Liu",
	title="Transfer Learning via Inter-Task Mappings for Temporal Difference Learning",
        journal="Journal of Machine Learning Research",
	year="2007",
	volume="8",number="1",
        pages="2125--2167",
	abstract="Temporal difference (TD) learning has become a
          popular reinforcement learning technique in recent years. TD
          methods, relying on function approximators to generalize
          learning to novel situations, have had some experimental
          successes and have been shown to exhibit some desirable
          properties in theory, but the most basic algorithms have
          often been found slow in practice. This empirical result has
          motivated the development of many methods that speed up
          reinforcement learning by modifying a task for the learner
          or helping the learner better generalize to novel
          situations. This article focuses on generalizing across
          tasks, thereby speeding up learning, via a novel form of
          transfer using handcoded task relationships. We compare
          learning on a complex task with three function
          approximators, a cerebellar model arithmetic computer
          (CMAC), an artificial neural network (ANN), and a radial
          basis function (RBF), and empirically demonstrate that
          directly transferring the action-value function can lead to
          a dramatic speedup in learning with all three. Using
          transfer via inter-task mapping (tvitm), agents are able to
          learn one task and then markedly reduce the time it takes to
          learn a more complex task. Our algorithms are fully
          implemented and tested in the RoboCup soccer Keepaway
          domain.",
}

Generated by bib2html.pl (written by Patrick Riley ) on Mon Nov 10, 2008 14:24:53