ICML-99 Best Paper Award

This paper was selected by vote by the members of the Program Committee. The following eight submitted papers that received the best reviews in the review process were nominated for the vote:

• Lazy Bayesian Rules: A Lazy Semi-Naive Bayesian Learning Technique Competitive to Boosting Decision Trees
  Zijian Zheng, Geoffrey I. Webb, and Kai Ming Ting
  

• Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
  by Andrew Y. Ng, Daishi Harada, and Stuart Russell
  

• Hierarchical Optimization of Policy-Coupled Semi-Markov Decision Processes
  by Gang Wang and Sridhar Mahadevan
  

• Discriminant Trees
  by Joao Gama
  

• Active Learning for Natural Language Parsing and Information Extraction
  by Cynthia A. Thompson, Mary Elaine Califf, and Raymond J. Mooney
  

• Transductive Inference for Text Classification using Support Vector Machines
  by Thorsten Joachims
  

• Large Margin Decision Trees for Induction and Transduction
  by Donghui Wu, Kristin P. Bennett, Nello Cristianini, and John Shawe-Taylor
  

• Least-Squares Temporal Difference Learning
  by Justin A. Boyan