Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits

v1v2v3v4v5v6 (latest)

Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits

19 July 2018

ArXiv (abs)PDF HTML

Papers citing "Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits"

6 / 56 papers shown

Title
Prediction with Corrupted Expert Advice I Zaghloul Amir Idan Attias Tomer Koren Roi Livni Yishay Mansour 59 40 0 24 Feb 2020
Corruption-robust exploration in episodic reinforcement learning Thodoris Lykouris Max Simchowitz Aleksandrs Slivkins Wen Sun 105 105 0 20 Nov 2019
Stochastic Linear Optimization with Adversarial Corruption Yingkai Li Edmund Y. Lou Liren Shan AAML 72 42 0 04 Sep 2019
Nonstochastic Multiarmed Bandits with Unrestricted Delays Tobias Sommer Thune Nicolò Cesa-Bianchi Yevgeny Seldin 84 53 0 03 Jun 2019
Better Algorithms for Stochastic Bandits with Adversarial Corruptions Anupam Gupta Tomer Koren Kunal Talwar AAML 144 153 0 22 Feb 2019
KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints Aurélien Garivier Hédi Hadiji Pierre Menard Gilles Stoltz 80 33 0 14 May 2018