Duff, Michael O.

6 publications

ICML 2003 Design for an Optimal Probe Michael O. Duff

ICML 2003 Diffusion Approximation for Bayesian Markov Chains Michael O. Duff

AISTATS 2001 Monte-Carlo Algorithms for the Improvement of Finite-State Stochastic Controllers: Application to Bayes-Adaptive Markov Decision Processes Michael O. Duff

NeurIPS 1996 Local Bandit Approximation for Optimal Learning Problems Michael O. Duff, Andrew G. Barto

ICML 1995 Q-Learning for Bandit Problems Michael O. Duff

NeurIPS 1994 Reinforcement Learning Methods for Continuous-Time Markov Decision Problems Steven J. Bradtke, Michael O. Duff