Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis

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 nondominated 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.

• Type: Conference
• Year: 2010
• Where: ICML
• Authors: Daniel J. Lizotte, Michael H. Bowling, Susan A. Murphy
• Keywords: Continuous State, ICML 2010, Machine Learning, Multiple Reward Functions, Randomized Controlled Trials