• Sorted by Date • Classified by Publication Type • Classified by Topic • Sorted by First Author Last Name •
Patrick MacAlpine, Mike Depinet, and Peter Stone. UT Austin Villa 2014: RoboCup 3D Simulation League Champion via Overlapping Layered Learning. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), pp. 2842–48, 4, January 2015.
Accompanying videos at http://www.cs.utexas.edu/ AustinVilla/sim/3dsimulation/AustinVilla3DSimulationFiles/2014/html/overlappingLayeredLearning.html
[PDF]714.7kB [postscript]2.5MB
Layered learning is a hierarchical machine learning paradigm that enables learning of complex behaviors by incrementally learning a series of sub-behaviors. A key feature of layered learning is that higher layers directly depend on the learned lower layers. In its original formulation, lower layers were frozen prior to learning higher layers. This paper considers an extension to the paradigm that allows learning certain behaviors independently, and then later stitching them together by learning at the "seams" where their influences overlap. The UT Austin Villa 2014 RoboCup 3D simulation team, using such overlapping layered learning, learned a total of 19 layered behaviors for a simulated soccer-playing robot, organized both in series and in parallel. To the best of our knowledge this is more than three times the number of layered behaviors in any prior layered learning system. Furthermore, the complete learning process is repeated on four different robot body types, showcasing its generality as a paradigm for efficient behavior learning. The resulting team won the RoboCup 2014 championship with an undefeated record, scoring 52 goals and conceding none. This paper includes a detailed experimental analysis of the team's performance and the overlapping layered learning approach that led to its success.
@InProceedings{AAAI15-MacAlpine2,
author = {Patrick MacAlpine and Mike Depinet and Peter Stone},
title = {{UT} {A}ustin {V}illa 2014: {R}obo{C}up 3{D} Simulation League Champion via Overlapping Layered Learning},
booktitle = {Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI)},
location = {Austin, Texas, USA},
month = {January},
year = {2015},
volume = 4,
pages = {2842--48},
abstract={
Layered learning is a hierarchical machine learning paradigm that enables
learning of complex behaviors by incrementally learning a series of
sub-behaviors. A key feature of layered learning is that higher layers directly
depend on the learned lower layers. In its original formulation, lower layers
were frozen prior to learning higher layers. This paper considers an extension
to the paradigm that allows learning certain behaviors independently, and then
later stitching them together by learning at the "seams" where their influences
overlap. The UT Austin Villa 2014 RoboCup 3D simulation team, using such
overlapping layered learning, learned a total of 19 layered behaviors for a
simulated soccer-playing robot, organized both in series and in parallel. To
the best of our knowledge this is more than three times the number of layered
behaviors in any prior layered learning system. Furthermore, the complete
learning process is repeated on four different robot body types, showcasing its
generality as a paradigm for efficient behavior learning. The resulting team
won the RoboCup 2014 championship with an undefeated record, scoring 52 goals
and conceding none. This paper includes a detailed experimental analysis of
the team's performance and the overlapping layered learning approach that led
to its success.
},
wwwnote={Accompanying videos at <a href="http://www.cs.utexas.edu/~AustinVilla/sim/3dsimulation/AustinVilla3DSimulationFiles/2014/html/overlappingLayeredLearning.html">http://www.cs.utexas.edu/~AustinVilla/sim/3dsimulation/AustinVilla3DSimulationFiles/2014/html/overlappingLayeredLearning.html</a>},
}
Generated by bib2html.pl (written by Patrick Riley ) on Tue Nov 19, 2024 10:29:29