Bandits and Explore/Exploit in RL
Some Recent Bandit Results
Deep Reinforcement Learning
Inferring Multiple Regulation Networks
lil’ UCB: An Optimal Exploration Algorithm for Multi-Armed Bandits
Learning Theory: statistical and game-theoretic approaches
Statistical Significance and Stability Analysis for Patterns
Distribution-Dependent PAC-Bayes Priors
Space Systems Engineering
Predicting Syntax: Processing Dative Constructions in American and Australian Varieties of English