TH2.R3.4

Minimax Regret with Unbounded Weights

Michael Drmota, TU Wien, Austria; Philippe Jacquet, INRIA, France; Changlong Wu, Wojciech Szpankowski, Purdue University, United States
Session:
Multi-Armed Bandits 2
Track:
8: Bandits
Location:
Ypsilon IV-V-VI
Presentation Time:
Thu, 11 Jul, 12:30 - 12:50
Session Chair:
Vincent Tan, National University of Singapore
Presentation
Not logged in.
Discussion
Not logged in.
Session TH2.R3
TH2.R3.1: BAI in Exponential Family: Efficiency and Optimality
Arpan Mukherjee, Ali Tajer, Rensselaer Polytechnic Institute, United States
TH2.R3.2: Best Arm Identification with Arm Erasures
Srinivas Reddy Kota, Indian Institute of Technology Madras, India; Karthik Periyapattana Narayana Prasad, Indian Institute of Technology Hyderabad, India; Vincent Y. F. Tan, National University of Singapore, Singapore
TH2.R3.3: Optimal Stopping Rules for Best Arm Identification in Stochastic Bandits under Uniform Sampling
Vedang Gupta, Yash Gadhia, Shivaram Kalyanakrishnan, Nikhil Karamchandani, Indian Institute of Technology Bombay, India
TH2.R3.4: Minimax Regret with Unbounded Weights
Michael Drmota, TU Wien, Austria; Philippe Jacquet, INRIA, France; Changlong Wu, Wojciech Szpankowski, Purdue University, United States
Resources
No resources available.