@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InCollection(LNAI98-tpot-rl,
        Author="Peter Stone and Manuela Veloso",
        Title="Team-Partitioned, Opaque-Transition Reinforcement Learning",
        booktitle= "{R}obo{C}up-98: Robot Soccer World Cup {II}",
        Editor="Minoru Asada and Hiroaki Kitano",
        series="Lecture Notes in Artificial Intelligence",      
	volume="1604",
	pages="261--72",
        Publisher="Springer Verlag",address="Berlin",year="1999",
        note= "Also in {\it Proceedings of the Third International Conference on
                  Autonomous Agents}, 1999",
        abstract={
                  We present a novel multi-agent learning paradigm
                  called team-partitioned, opaque-transition
                  reinforcement learning (TPOT-RL).  TPOT-RL
                  introduces the use of action-dependent features to
                  generalize the state space.  In our work, we use a
                  {\it learned} action-dependent feature space to aid
                  higher-level reinforcement learning.  TPOT-RL is an
                  effective technique to allow a team of agents to
                  learn to cooperate towards the achievement of a
                  specific goal.  It is an adaptation of traditional
                  RL methods that is applicable in complex,
                  non-Markovian, multi-agent domains with large state
                  spaces and limited training opportunities.  TPOT-RL
                  is fully implemented and has been tested in the
                  robotic soccer domain, a complex, multi-agent
                  framework.  This paper presents the algorithmic
                  details of TPOT-RL as well as empirical results
                  demonstrating the effectiveness of the developed
                  multi-agent learning approach with learned features.
  },
)