Are sample means in multi-armed bandits positively or negatively biased?

27 May 2019

Papers citing "Are sample means in multi-armed bandits positively or negatively biased?"

10 / 10 papers shown

Title
Replicability is Asymptotically Free in Multi-armed Bandits Junpei Komiyama Shinji Ito Yuichi Yoshida Souta Koshino 35 1 0 12 Feb 2024
Entropy Regularization for Population Estimation Ben Chugg Peter Henderson Jacob Goldin Daniel E. Ho 28 3 0 24 Aug 2022
Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization Tong Li Jacob Nogas Haochen Song Harsh Kumar A. Durand Anna N. Rafferty Nina Deliu S. Villar Joseph Jay Williams 31 5 0 15 Dec 2021
Safe Data Collection for Offline and Online Policy Learning Ruihao Zhu B. Kveton OffRL 19 5 0 08 Nov 2021
Metalearning Linear Bandits by Prior Update Amit Peleg Naama Pearl Ron Meir 39 18 0 12 Jul 2021
Near-optimal inference in adaptive linear regression K. Khamaru Y. Deshpande Tor Lattimore Lester W. Mackey Martin J. Wainwright 30 16 0 05 Jul 2021
Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits Wenshuo Guo Kumar Krishna Agrawal Aditya Grover Vidya Muthukumar A. Pananjady 16 8 0 28 Jun 2021
Policy Learning with Adaptively Collected Data Ruohan Zhan Zhimei Ren Susan Athey Zhengyuan Zhou OffRL 45 27 0 05 May 2021
Challenges in Statistical Analysis of Data Collected by a Bandit Algorithm: An Empirical Exploration in Applications to Adaptively Randomized Experiments Joseph Jay Williams Jacob Nogas Nina Deliu Hammad Shaikh S. Villar A. Durand Anna N. Rafferty AAML 30 10 0 22 Mar 2021
Inference for Batched Bandits Kelly W. Zhang Lucas Janson Susan Murphy 28 80 0 08 Feb 2020