dblp.uni-trier.dewww.uni-trier.de

Michael O. Duff

List of publications from the DBLP Bibliography Server - FAQ
Coauthor Index - Ask others: ACM DL/Guide - CiteSeer - CSB - Google - MSN - Yahoo

2003
6 Michael O. Duff: Design for an Optimal Probe. ICML 2003: 131-138
5 Michael O. Duff: Diffusion Approximation for Bayesian Markov Chains. ICML 2003: 139-146
1996
4EEMichael O. Duff, Andrew G. Barto: Local Bandit Approximation for Optimal Learning Problems. NIPS 1996: 1019-1025
1995
3 Michael O. Duff: Q-Learning for Bandit Problems. ICML 1995: 209-217
1994
2EESteven J. Bradtke, Michael O. Duff: Reinforcement Learning Methods for Continuous-Time Markov Decision Problems. NIPS 1994: 393-400
1993
1EEAndrew G. Barto, Michael O. Duff: Monte Carlo Matrix Inversion and Reinforcement Learning. NIPS 1993: 687-694

Coauthor Index

1Andrew G. Barto [1] [4]
2Steven J. Bradtke [2]

Copyright © Sun May 17 03:24:02 2009 by Michael Ley (ley@uni-trier.de)