Sciweavers

38 search results - page 4 / 8
» icml 1998
Sort
View
ICML
1998
IEEE
14 years 10 months ago
The Case against Accuracy Estimation for Comparing Induction Algorithms
We analyze critically the use of classi cation accuracy to compare classi ers on natural data sets, providing a thorough investigation using ROC analysis, standard machine learnin...
Foster J. Provost, Tom Fawcett, Ron Kohavi
ICML
1998
IEEE
14 years 1 months ago
The Problem with Noise and Small Disjuncts
Many systems that learn from examples express the learned concept as a disjunction. Those disjuncts that cover only a few examples are referred to as small disjuncts. The problem ...
Gary M. Weiss, Haym Hirsh
ICML
1998
IEEE
14 years 10 months ago
Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
In this paper, we adopt general-sum stochastic games as a framework for multiagent reinforcement learning. Our work extends previous work by Littman on zero-sum stochastic games t...
Junling Hu, Michael P. Wellman
ICML
1998
IEEE
14 years 10 months ago
A Randomized ANOVA Procedure for Comparing Performance Curves
Three factors are related in analyses of performance curves such as learning curves: the amount of training, the learning algorithm, and performance. Often we want to know whether...
Justus H. Piater, Paul R. Cohen, Xiaoqin Zhang, Mi...
ICML
1998
IEEE
14 years 10 months ago
RL-TOPS: An Architecture for Modularity and Re-Use in Reinforcement Learning
This paper introduces the RL-TOPs architecture for robot learning, a hybrid system combining teleo-reactive planning and reinforcement learning techniques. The aim of this system ...
Malcolm R. K. Ryan, Mark D. Pendrith