Towards an optimal scoring policy for simulated soccer agents

Jelle R. Kok, Remco de Boer, and Nikos Vlassis. Towards an optimal scoring policy for simulated soccer agents. In Proceedings of the International Conference on Intelligent Autonomous Systems, pp. 195–198, IOS Press, Marina del Rey, California, March 2002.
Publisher's Webpage© Springer-Verlag

Download

pdf [209.3kB]  ps.gz [133.4kB]  

Abstract

This paper describes the scoring policy used by the agents of our simulation robot soccer team. In a given situation this policy enables an agent to determine the best shooting point in the goal, together with an associated probability of scoring when the ball is shot to this point. The ball motion can be regarded as a geometrically constrained continuous-time Markov process. Our main contribution is an approximate method for learning relevant statistics of such a process.

BibTeX Entry

@InProceedings{Kok02ias,
  author =       {Jelle R. Kok and Remco de Boer and Nikos Vlassis},
  title =        {Towards an optimal scoring policy for simulated
                  soccer agents},
  booktitle =    {Proceedings of the International Conference on
                  Intelligent Autonomous Systems},
  address =      {Marina del Rey, California},
  editor =       {M. Gini and W. Shen and C. Torras and H. Yuasa},
  publisher =    {IOS Press},
  pages =        {195--198},
  year =         {2002},
  month =        mar,
  postscript =   {2002/Kok02ias.ps.gz},
  pdf =          {2002/Kok02ias.pdf},
  abstract =     {This paper describes the scoring policy used by the
                  agents of our simulation robot soccer team. In a
                  given situation this policy enables an agent to
                  determine the best shooting point in the goal,
                  together with an associated probability of scoring
                  when the ball is shot to this point. The ball motion
                  can be regarded as a geometrically constrained
                  continuous-time Markov process. Our main
                  contribution is an approximate method for learning
                  relevant statistics of such a process. }
}

---

Generated by bib2html.pl (written by Patrick Riley) on Tue Oct 31, 2006 19:33:42 UTC