Peter Stone's Selected Publications

• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •

Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function

Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function.
Peter Stone and Manuela Veloso.
In Advances in Neural Information Processing Systems 8, pp. 896–902, MIT Press, Cambridge, MA, 1996.
NIPS-95
HTML version.

Download

[PDF]300.1kB  [postscript]1.8MB  

Abstract

Learning how to adjust to an opponent's position is critical to the success of having intelligent agents collaborating towards the achievement of specific tasks in unfriendly environments. This paper describes our work on a Memory-based technique for to choose an action based on a continuous-valued state attribute indicating the position of an opponent. We investigate the question of how an agent performs in nondeterministic variations of the training situations. Our experiments indicate that when the random variations fall within some bound of the initial training, the agent performs better with some initial training rather than from a tabula-rasa.

BibTeX Entry

@InProceedings(NIPS95,
        Author="Peter Stone and Manuela Veloso",
        title="Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function", 
        booktitle="Advances in Neural Information Processing Systems 8",
        editor="David S.~Touretzky and Michael C.~Mozer and 
                Michael E.~Hasselmo",
        pages="896--902",
        year="1996",
        publisher="{MIT} Press",
        address="Cambridge, MA",
        abstract={
                  Learning how to adjust to an opponent's position is
                  critical to the success of having intelligent agents
                  collaborating towards the achievement of specific
                  tasks in unfriendly environments.  This paper
                  describes our work on a Memory-based technique for
                  to choose an action based on a continuous-valued
                  state attribute indicating the position of an
                  opponent. We investigate the question of how an
                  agent performs in nondeterministic variations of the
                  training situations.  Our experiments indicate that
                  when the random variations fall within some bound of
                  the initial training, the agent performs better with
                  some initial training rather than from a
                  tabula-rasa.
        },
  wwwnote={<a href="http://www.nips.snl.salk.edu/">NIPS-95</a><br>
           <a href="http://www.cs.utexas.edu/~pstone/Papers/95nips/Membased-tech.html">HTML version</a>.},
)

Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 17, 2024 18:42:57