Varun Kanade

Addressing environment non-stationarity by repeating Q-learning updates

Taking the Human Out of the Loop: A Review of Bayesian Optimization

Optimal Experimental Design for Staggered Rollouts

Balanced Linear Contextual Bandits

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems

Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications

Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions

Sleeping Experts and Bandits with Stochastic Action Availability and Adversarial Rewards