Tailoring Action Parameterizations to Their Task Contexts (bibtex)
by Freek Stulp, Michael Beetz
Abstract:
Solving complex tasks successfully and efficiently not only depends on \em what you do, but also \em how you do it. Different task contexts have different performance measures, and thus require different ways of executing an action to optimize performance. Simply adding new actions that are tailored to perform well within a specific task context makes planning or action selection programming more difficult, as generality and adaptivity is lost. Rather, existing actions should be parametrized such that they optimize the task-specific performance measure. In this paper we propose a novel computation model for the execution of abstract action chains. In this computation model, a robot first learns situation-specific performance models of abstract actions. It then uses these models to automatically specialize the abstract actions for their execution in a given action chain. This specialization results in refined chains that are optimized for performance. As a side effect this behavior optimization also appears to produce action chains with seamless transitions between actions.
Reference:
Freek Stulp, Michael Beetz, "Tailoring Action Parameterizations to Their Task Contexts", IJCAI Workshop ``Agents in Real-Time and Dynamic Environments'', 2005. IJCAI Workshop ``Agents in Real-Time and Dynamic Environments''
Bibtex Entry:
@Misc{stulp05tailoring,
  author            = {Freek Stulp and Michael Beetz},
  title             = {Tailoring Action Parameterizations to Their Task Contexts},
  note              = {IJCAI Workshop ``Agents in Real-Time and Dynamic Environments''},
  year              = {2005},
  url               = {http://www.tzi.de/\~visser/ijcai05/},
  bib2html_pubtype  = {Refereed Workshop Paper},
  bib2html_rescat   = {Models, Learning, Planning, Action},
  bib2html_groups   = {IAS, AGILO},
  bib2html_keywords = {},
  abstract          = {Solving complex tasks successfully and efficiently not
  only depends on {\em what} you do, but also {\em how} you do it. Different
  task contexts have different performance measures, and thus require different
  ways of executing an action to optimize performance. Simply adding new actions
  that are tailored to perform well within a specific task context makes
  planning or action selection programming more difficult, as generality and
  adaptivity is lost. Rather, existing actions should be parametrized such that
  they optimize the task-specific performance measure. In this paper we propose
  a novel computation model for the execution of abstract action chains. In this
  computation model, a robot first learns situation-specific performance models
  of abstract actions. It then uses these models to automatically specialize the
  abstract actions for their execution in a given action chain. This
  specialization results in refined chains that are optimized for performance.
  As a side effect this behavior optimization also appears to produce action
  chains with seamless transitions between actions.}
}
Powered by bibtexbrowser