• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Daniel Urieli, Patrick MacAlpine, Shivaram Kalyanakrishnan, Yinon Bentor, and Peter Stone. Optimizing Interdependent Skills for Simulated 3D Humanoid Robot Soccer. In The Fifth Workshop on Humanoid Soccer Robots at Humanoids 2010, December 2010.
[PDF]338.7kB [postscript]856.2kB
In several realistic domains an agent's behavior is composed of multiple interdependent skills. For example, consider a humanoid robot that must play soccer, as is the focus of this paper. In order to succeed, it is clear that the robot needs to walk quickly, turn sharply, and kick the ball far. However, these individual skills are ineffective if the robot falls down when switching from walking to turning, or if it cannot position itself behind the ball for a kick. This paper presents a learning architecture for a humanoid robot soccer agent that has been fully deployed and tested within the RoboCup 3D simulation environment. First, we demonstrate that individual skills such as walking and turning can be parameterized and optimized to match the best performance statistics reported in the literature. These results are achieved through effective use of the CMA-ES optimization algorithm. Next, we describe a framework for optimizing skills in conjunction with one another, a little-understood problem with substantial practical significance. Over several phases of learning, a total of roughly 100--150 parameters are optimized. Detailed experiments show that an agent thus optimized performs comparably with the top teams from the RoboCup 2010 competitions, while taking relatively few man-hours for development.
@InProceedings{HUMANOIDS10-urieli,
author = "Daniel Urieli and Patrick MacAlpine and Shivaram Kalyanakrishnan and Yinon Bentor and Peter Stone",
title = "Optimizing Interdependent Skills for Simulated 3D Humanoid Robot Soccer",
booktitle = "The Fifth Workshop on Humanoid Soccer Robots at Humanoids 2010",
location = "Nashville, TN",
month = "December",
year = "2010",
abstract = {
In several realistic domains an agent's behavior is composed of multiple
interdependent skills. For example, consider a humanoid robot that must
play soccer, as is the focus of this paper. In order to succeed, it is
clear that the robot needs to walk quickly, turn sharply, and kick the
ball far. However, these individual skills are ineffective if the robot
falls down when switching from walking to turning, or if it cannot
position itself behind the ball for a kick.
This paper presents a learning architecture for a humanoid robot soccer
agent that has been fully deployed and tested within the RoboCup 3D
simulation environment. First, we demonstrate that individual skills
such as walking and turning can be parameterized and optimized to match
the best performance statistics reported in the literature. These
results are achieved through effective use of the CMA-ES optimization
algorithm. Next, we describe a framework for optimizing skills in
conjunction with one another, a little-understood problem with
substantial practical significance. Over several phases of learning, a
total of roughly 100--150 parameters are optimized. Detailed experiments
show that an agent thus optimized performs comparably with the top teams
from the RoboCup 2010 competitions, while taking relatively few
man-hours for development.
},
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Jan 26, 2011 15:32:31