collaborators

5 papers

stat.ML2026

Implicit Q-Learning and SARSA: Liberating Policy Control from Step-Size Calibration

Hwanwoo Kim, Eric Laber

Q-learning and SARSA are foundational reinforcement learning algorithms whose practical success depends critically on step-size calibration. Step-sizes that are too large can cause…

stat.ML2025

Implicit Updates for Average-Reward Temporal Difference Learning

Hwanwoo Kim, Dongkyu Derek Cho, Eric Laber

Temporal difference (TD) learning is a cornerstone of reinforcement learning. In the average-reward setting, standard TD() is highly sensitive to the choice of step-size and th…

stat.ML2025

Efficient optimization of expensive black-box simulators via marginal means, with application to neutrino detector design

Hwanwoo Kim, Simon Mak, Ann-Kathrin Schuetz +1

With advances in scientific computing, computer experiments are increasingly used for optimizing complex systems. However, for modern applications, e.g., the optimization of nuclea…

cs.LG2025

Stabilizing Temporal Difference Learning via Implicit Stochastic Recursion

Hwanwoo Kim, Panos Toulis, Eric Laber

Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL). For nearly forty years, TD learning has served as a workhorse for applied RL as well a…

stat.ML2025

Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?

Hwanwoo Kim, Chong Liu, Yuxin Chen

Bayesian optimization (BO) is a widely used iterative algorithm for optimizing black-box functions. Each iteration requires maximizing an acquisition function, such as the upper co…