Min-hwan Oh

Convergence of Muon with Newton-Schulz

Peng's Q($\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning

KL-Regularization Is Sufficient in Contextual Bandits and RLHF

Optimal Batched (Generalized) Linear Contextual Bandit Algorithm

Offline Preference-Based Value Optimization

Diversified Multinomial Logit Contextual Bandits

Batched Stochastic Matching Bandits

Blessings of Many Good Arms in Multi-Objective Linear Bandits

Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality

Sample-Efficient Pruning Model Selection via Lasso

Inverse GFlowNets for Generative Imitation Learning

Exploration via Feature Perturbation in Contextual Bandits

True Impact of Cascade Length in Contextual Cascading Bandits

Infrequent Exploration in Linear Bandits

Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems

Improved Online Confidence Bounds for Multinomial Logistic Bandits

Thompson Sampling for Multi-Objective Linear Contextual Bandit

Minimax Optimal Reinforcement Learning with Quasi-Optimism

Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning

Oracle-Efficient Combinatorial Semi-Bandits

Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options

ADAM Optimization with Adaptive Batch Selection

Dynamic Assortment Selection and Pricing with Censored Preference Feedback

EUGens: Efficient, Unified and General Dense Layers

Lasso Bandit with Compatibility Condition on Optimal Arm

Combinatorial Reinforcement Learning with Preference Feedback

Symmetry-Aware GFlowNets

GFlowNets Need Automorphism Correction for Unbiased Graph Generation

Combinatorial Reinforcement Learning with Preference Feedback

Optimal and Practical Batched Linear Bandit Algorithm

Magnituder Layers for Implicit Neural Representations in 3D

Linear Bandits with Partially Observable Features

Stochastic Matching Bandits under Preference Feedback

Linear Bandits with Partially Observable Features

Neural Dynamic Pricing: Provable and Practical Efficiency

Mostly Exploration-free Algorithms for Multi-Objective Linear Bandits

Coordinated Exploration in Distributed Reinforcement Learning