Links & Groups
Links to research groups working on multi-armed bandit algorithms and web resources.
Web Links
Leading Researchers
Tor Lattimore
DeepMind - Theoretical foundations, textbook author
Csaba Szepesvári
DeepMind & U. Alberta - Theory and algorithms, textbook author
Sébastien Bubeck
OpenAI (formerly Microsoft Research) - Theoretical advances
Benjamin Van Roy
Stanford University - Thompson Sampling, posterior sampling
Dylan Foster
Microsoft Research - Contextual bandits, online learning
Daniel Hsu
Columbia University - Statistical learning, contextual bandits
Alekh Agarwal
Microsoft Research - Contextual bandits at scale
Stuart Russell
UC Berkeley - Applications to AI safety and decision making
Research Teams
SIERRA Team
INRIA & ENS Paris - Sequential learning and RL
SCOOL Team
INRIA Lille - Statistical online learning
DeepMind
London, UK - Large-scale applications, theory
MSR ML Group
Microsoft Research - Contextual bandits, Vowpal Wabbit
BAIR
UC Berkeley - Deep RL and bandits
Stanford AI Lab
Stanford University - Theory and applications
mv

















