Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
International Conference on Machine Learning, Volume abs/1901.00301, 2019, Pages 7335-7344.
We investigate the feasibility of learning from both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying learning signal may be different between these two data sources. Theoretically, we state and prove no-regret algorithms for learning that is robust to divergences between ...More
PPT (Upload PPT)