John Langford Contextual Bandit workshop - ICML 2017 Sydney- real world interactive learning
The Contextual Bandits Problem: A New, Fast, and Simple Algorithm
Spring 2021 LIDS Seminar — John Langford (Microsoft)
Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits
John Langford - Real World Reinforcement Learning
Research talk: Post-contextual-bandit inference
PWL - QCon NYC Edition | John Langford on Making Contextual Decisions with Low Technical Debt
cb exploration
Latent State Recovery in Reinforcement Learning - John Langford
Real World Reinforcement Learning - John Langford
The Contextual Bandits Problem
Strategic Exploration via State Abstraction from Rich Observations - John Langford
Efficient Contextual Bandits in Non-stationary Worlds
Foundations of Real-World Reinforcement Learning
An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives
John Langford - A Deployable Decision Service - The Frontiers of Machine Learning
John S. Langford
John Langford - Vowpal Wabbit, the Next Generation
The Learning Salon - John Langford
An Ensemble Approach for News Recommendation Based on Contextual Bandit Algorithms