Multi-Agent Learning

• Pseudo-convergent Q-Learning by Competitive Pricebots (January 31, 2000)
  By Jeffrey O. Kephart and Gerald J. Tesauro
  To appear in Proceedings of Seventeenth International Conference on Machine Learning. Stanford University, CA, June 29-July 2, 2000.
  [Postscript] [gzip'd Postscript] [pdf]

 
• Multi-agent Q-Learning and Regression Trees for Automated Pricing Decisions (January 31, 2000)
  By Manu Sridharan and Gerald J. Tesauro
  To appear in Proceedings of Seventeenth International Conference on Machine Learning. Stanford University, CA, June 29-July 2, 2000.
  [Postscript] [gzip'd Postscript] [pdf]

 
• Pricing in Agent Economies Using Neural Networks and Multi-Agent Q-learning (August 2, 1999)
  By Gerald J. Tesauro
  Proceedings of Workshop ABS-3: Learning About, From and With other Agents. Stockholm, August 2, 1999.
  [Postscript] [pdf]

 
• Pricing in Agent Economies with Multi-Agent Q-learning (July 6, 1999)
  By Gerald J. Tesauro and Jeffrey O. Kephart
  Proceedings of Workshop on Decision Theoretic and Game Theoretic Agents. University College London, London, July 6, 1999.
  [Postscript] [pdf]

 
• Foresight-based Pricing Algorithms in an Economy of Software Agents
  (August 15, 1998)
  By Gerald J. Tesauro and Jeffrey O. Kephart
  Presented by Tesauro at International Conference on Information and Computation Economies, October, 1998.
  [Postscript] [pdf]