Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Team-Partitioned, Opaque-Transition Reinforcement Learning

Peter Stone and Manuela Veloso. Team-Partitioned, Opaque-Transition Reinforcement Learning. In Minoru Asada and Hiroaki Kitano, editors, RoboCup-98: Robot Soccer World Cup II, Lecture Notes in Artificial Intelligence, pp. 261–72, Springer Verlag, Berlin, 1999. Also in Proceedings of the Third International Conference on Autonomous Agents, 1999

Download

[PDF]151.4kB  [postscript]144.7kB  

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 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.

BibTeX Entry

@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.
  },
)

Generated by bib2html.pl (written by Patrick Riley ) on Wed Jul 09, 2014 11:54:42