Bandit Regret Scaling with the Effective Loss Range

15 May 2017

Papers citing "Bandit Regret Scaling with the Effective Loss Range"

5 / 5 papers shown

Title
An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits P. Auer Chao-Kai Chiang 22 110 0 27 May 2016
Refined Lower Bounds for Adversarial Bandits Sébastien Gerchinovitz Tor Lattimore AAML 41 59 0 24 May 2016
Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback N. Alon Nicolò Cesa-Bianchi Claudio Gentile Shie Mannor Yishay Mansour Ohad Shamir OffRL 147 130 0 30 Sep 2014
Online Learning with Predictable Sequences Alexander Rakhlin Karthik Sridharan 112 355 0 18 Aug 2012
From Bandits to Experts: On the Value of Side-Observations Shie Mannor Ohad Shamir OffRL 126 220 0 13 Jun 2011