Joongkyu Lee

reinforcement learning (2) regret bound (2) uncertainty quantification (1) policy learning (1) markov decision process (1) assortment optimization (1) optimistic exploration (1) temporal abstraction (1) multinomial logit (1) minimax regret (1) optimistic sampling (1) contextual bandit (1) ensemble method (1) exploration strategy (1) randomized exploration (1) multinomial logistic (1) frequentist regret (1) transition model (1) action repetition (1) multinomial logistic model (1)