• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Concurrent Layered Learning.
Shimon Whiteson and Peter Stone.
In Second International Joint Conference on Autonomous Agents
and Multiagent Systems, pp. 193–200, ACM Press, New York, NY, July 2003.
AAMAS-2003
[PDF]159.1kB [postscript]372.6kB
Hierarchies are powerful tools for decomposing complex control tasks into manageable subtasks. Several hierarchical approaches have been proposed for creating agents that can execute these tasks. Layered learning is such a hierarchical paradigm that relies on learning the various subtasks necessary for achieving the complete high-level goal. Layered learning prescribes training low-level behaviors (those closer to the environmental inputs) prior to high-level behaviors. In past implementations these lower-level behaviors were always frozen before advancing to the next layer. In this paper, we hypothesize that there are situations where layered learning would work better were the lower layers allowed to keep learning concurrently with the training of subsequent layers, an approach we call concurrent layered learning. We identify a situation where concurrent layered learning is beneficial and present detailed empirical results verifying our hypothesis. In particular, we use neuro-evolution to concurrently learn two layers of a layered learning approach to a simulated robotic soccer keepaway task. The main contribution of this paper is evidence that there exist situations where concurrent layered learning outperforms traditional layered learning. Thus, we establish that, when using layered learning, the concurrent training of layers can be an effective option.
@InProceedings(AAMAS03,
author="Shimon Whiteson and Peter Stone",
title="Concurrent Layered Learning",
booktitle="Second International Joint Conference on Autonomous Agents and Multiagent Systems",
month="July",year="2003",
pages="193--200",
publisher="{ACM} Press",
address="New York, NY",
editor="Jeffrey S.~Rosenschein and Tuomas Sandholm and Michael Wooldridge and Makoto Yokoo",
abstract={
Hierarchies are powerful tools for decomposing
complex control tasks into manageable subtasks.
Several hierarchical approaches have been proposed
for creating agents that can execute these tasks.
Layered learning is such a hierarchical paradigm
that relies on learning the various subtasks
necessary for achieving the complete high-level
goal. Layered learning prescribes training
low-level behaviors (those closer to the
environmental inputs) prior to high-level behaviors.
In past implementations these lower-level behaviors
were always frozen before advancing to the next
layer. In this paper, we hypothesize that there are
situations where layered learning would work better
were the lower layers allowed to keep learning
concurrently with the training of subsequent layers,
an approach we call concurrent layered learning. We
identify a situation where concurrent layered
learning is beneficial and present detailed
empirical results verifying our hypothesis. In
particular, we use neuro-evolution to concurrently
learn two layers of a layered learning approach to a
simulated robotic soccer keepaway task. The main
contribution of this paper is evidence that there
exist situations where concurrent layered learning
outperforms traditional layered learning. Thus, we
establish that, when using layered learning, the
concurrent training of layers can be an effective
option.
},
wwwnote={<a href="http://www.aamas-conference.org/">AAMAS-2003</a>},
)
Generated by bib2html.pl (written by Patrick Riley ) on Tue Nov 19, 2024 10:24:46