UT Austin Villa Publications

Sorted by DateClassified by Publication TypeClassified by TopicSorted by First Author Last Name

Adaptation of Surrogate Tasks for Bipedal Walk Optimization

Patrick MacAlpine, Elad Liebman, and Peter Stone. Adaptation of Surrogate Tasks for Bipedal Walk Optimization. In GECCO Surrogate-Assisted Evolutionary Optimisation (SAEOpt) Workshop, July 2016.

Download

[PDF]172.1kB  [postscript]739.5kB  

Abstract

In many learning and optimization tasks, the sample cost of performing the task is prohibitively expensive or time consuming. For this reason, attempting to directly employ a learning algorithm on the task could quickly become intractable. For this reason, learning is instead often performed on a less expensive task that is believed to be a reasonable approximation or a surrogate of the actual target task. This paper serves to present and motivate the challenging open problem of simultaneously performing learning on an approximation of the true target task, while at the same time adapting the surrogate task used for learning to be a better representation of the true target task. Our work, which is still in progress, is performed in the RoboCup 3D simulation environment where we attempt to learn the configuration parameters for an omnidirectional walk engine used by humanoid robot soccer playing agents.

BibTeX

@InProceedings{SAEO16-MacAlpine,
  author = {Patrick MacAlpine and Elad Liebman and Peter Stone},
  title = {Adaptation of Surrogate Tasks for Bipedal Walk Optimization},
  booktitle = {GECCO Surrogate-Assisted Evolutionary Optimisation (SAEOpt) Workshop},
  location = {Denver, Colorado, USA},
  month = {July},
  year = {2016},
  abstract={
    In many learning and optimization tasks, the sample cost of performing the 
task is prohibitively expensive or time consuming. For this reason, attempting 
to directly employ a learning algorithm on the task could quickly become 
intractable. For this reason, learning is instead often performed on a less 
expensive task that is believed to be a reasonable approximation or a surrogate 
of the actual target task.  This paper serves to present and motivate the 
challenging open problem of simultaneously performing learning on an 
approximation of the true target task, while at the same time adapting the 
surrogate task used for learning to be a better representation of the true 
target task.  Our work, which is still in progress, is performed in the RoboCup 
3D simulation environment where we attempt to learn the configuration 
parameters for an omnidirectional walk engine used by humanoid robot soccer 
playing agents. 
}
}

Generated by bib2html.pl (written by Patrick Riley ) on Thu Oct 12, 2017 13:11:26