Michael O. Duff

According to our database, Michael O. Duff authored at least 7 papers between 1993 and 2003.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2003

Diffusion Approximation for Bayesian Markov Chains.

Michael O. Duff

Proceedings of the Machine Learning, 2003

Design for an Optimal Probe.

Michael O. Duff

Proceedings of the Machine Learning, 2003

2001

Monte-Carlo Algorithms for the Improvement of Finite-State Stochastic Controllers: Application to Bayes-Adaptive Markov Decision Processes.

Michael O. Duff

Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, 2001

1996

Local Bandit Approximation for Optimal Learning Problems.

Michael O. Duff, Andrew G. Barto

Proceedings of the Advances in Neural Information Processing Systems 9, 1996

1995

Q-Learning for Bandit Problems.

Michael O. Duff

Proceedings of the Machine Learning, 1995

1994

Reinforcement Learning Methods for Continuous-Time Markov Decision Problems.

Steven J. Bradtke, Michael O. Duff

Proceedings of the Advances in Neural Information Processing Systems 7, 1994

1993

Monte Carlo Matrix Inversion and Reinforcement Learning.

Andrew G. Barto, Michael O. Duff

Proceedings of the Advances in Neural Information Processing Systems 6, 1993