Sumeet Katariya

multi-armed bandit (8) regret bound (6) sample complexity (3) bandit algorithm (3) bayes regret (2) bayesian optimization (2) ucb algorithm (2) upper confidence bound (2) thompson sampling (2) online learning (2) bayesian inference (1) policy learning (1) explainable ai (1) multitask learning (1) probabilistic modeling (1) offline reinforcement learning (1) self-supervised learning (1) dynamic programming (1) logical reasoning (1) exploration-exploitation tradeoff (1)