36 citations · 37 across the 6 of their papers we have counts for
5 papers · 1 filter
The Surrogate Is Not the Reward: Post-Surrogate Primary-Outcome Acquisition in Contextual Bandits
Kyungbok Lee, Michael R. Kosorok
We study contextual bandits in which a surrogate is observed after the action but before the learner decides whether to acquire the primary outcome that defines action value and re…
Provable Offline Reinforcement Learning for Structured Cyclic MDPs
Kyungbok Lee, Angelica Cristello Sarteau, Michael R. Kosorok
We introduce a novel cyclic Markov decision process (MDP) framework for multi-step decision problems with heterogeneous stage-specific dynamics, transitions, and discount factors a…
Doubly-Robust Off-Policy Evaluation with Estimated Logging Policy
Kyungbok Lee, Myunghee Cho Paik
We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov decision processes, DRUnknown, designed for situations where both the logging policy and th…
Wasserstein Geodesic Generator for Conditional Distributions
Young-geun Kim, Kyungbok Lee, Youngwon Choi +2
Generating samples given a specific label requires estimating conditional distributions. We derive a tractable upper bound of the Wasserstein distance between conditional distribut…
Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits
Wonyoung Kim, Kyungbok Lee, Myunghee Cho Paik
We propose a novel contextual bandit algorithm for generalized linear rewards with an regret over rounds where is the minimum eigenvalue of th…