Follow
Yichun Hu
Yichun Hu
Verified email at cornell.edu - Homepage
Title
Cited by
Cited by
Year
Smooth contextual bandits: Bridging the parametric and non-differentiable regret regimes
Y Hu, N Kallus, X Mao
Conference on Learning Theory, 2007-2010, 2020
212020
Fast rates for contextual linear optimization
Y Hu, N Kallus, X Mao
Management Science, 2022
92022
Fast rates for the regret of offline reinforcement learning
Y Hu, N Kallus, M Uehara
arXiv preprint arXiv:2102.00479, 2021
62021
DTR Bandit: Learning to Make Response-Adaptive Decisions With Low Regret
Y Hu, N Kallus
arXiv preprint arXiv:2005.02791, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–4