Mon, Oct 24 at noon:
Academic innovation & the global public research university, James Hilton
Lizotte, Daniel, M. Bowling, and Susan A. Murphy. 2010. "Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis." In Proceedings of the 27th International Conference on Machine Learning (ICML 2010) edited by Johannes Furnkranz and Thorsten Joachims. Madison, WI: International Machine Learning Society.
We introduce new, efficient algorithms for value iteration with multiple reward functions and continuous state. We also give an algorithm for finding the set of all non-dominated actions in the continuous state setting. This novel extension is appropriate for environments with continuous or finely discretized states where generalization is required, as is the case for data analysis of randomized controlled trials.