(Inverse Bandit) Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits
This is a recap of the “inverse bandit” problem first proposed in this paper.
About me
Hi, I’m Hao Qin, a forth-year PhD student at The University of Arizona in the program of GIDP-STATS. I am fortunately advised by Prof. Chicheng Zhang. Before that, I received my Bachelor degree in Applied Mathematics from Shandong University and Master degree in Data Science from The University of Wisconsin-Madison.Research Interests
I am interested in the theoretical analysis of the reinforcement learning algorithms including multi-armed bandit algorithms and MDPs. Also, I am interested in finding the reward to align with the properse of training. Currently, I am working on the following directions:- Multi-armed bandits
- Markov Decision Processing
- Reward Modeling
Publications
News
(SCAL) Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning
This is a recap of the regert analysis in SCAL.
(UCRL2) Near-optimal Regret Bounds for Reinforcement Learning
This is a recap of the regert analysis in UCRL2.
Multi-armed Bandits with Bounded Rewards a Short Survey
Here is a short survey covering the most common seen Multi-armed bandits (MAB) algorithms. You can download the full survey here.