Min-hwan Oh

Venues

Frequent coauthors

Papers

1. Unified Framework of Distributional Regret in Multi-Armed Bandits and Reinforcement Learning
   COLT 2026 ·

   Harin Lee

   DBLP profile ↗ORCID search ↗
2. ADAM Optimization with Adaptive Batch Selection
   ICLR 2025 ·

   Gyu-Yeol Kim

   DBLP profile ↗ORCID search ↗
3. Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning
   ICLR 2025 ·

   Hyungkyu Kang

   DBLP profile ↗ORCID search ↗
4. Combinatorial Reinforcement Learning with Preference Feedback
   ICML 2025 ·

   Joongkyu Lee

   DBLP profile ↗ORCID search ↗
5. Dynamic Assortment Selection and Pricing with Censored Preference Feedback
   ICLR 2025 ·

   Jung-hun Kim

   DBLP profile ↗ORCID search ↗
6. EUGens: Efficient, Unified and General Dense Layers
   NeurIPS 2025 ·

   Sang Min Kim

   DBLP profile ↗ORCID search ↗
7. Experimental Design for Semiparametric Bandits
   COLT 2025 ·

   Seok-Jin Kim

   DBLP profile ↗ORCID search ↗
8. Exploration via Feature Perturbation in Contextual Bandits
   NeurIPS 2025 ·

   Seouh-won Yi

   DBLP profile ↗ORCID search ↗
9. Improved Online Confidence Bounds for Multinomial Logistic Bandits
   ICML 2025 ·

   Joongkyu Lee

   DBLP profile ↗ORCID search ↗
10. Infrequent Exploration in Linear Bandits
    NeurIPS 2025 ·

    Harin Lee

    DBLP profile ↗ORCID search ↗
11. Lasso Bandit with Compatibility Condition on Optimal Arm
    ICLR 2025 ·

    Harin Lee

    DBLP profile ↗ORCID search ↗
12. Linear Bandits with Partially Observable Features
    ICML 2025 ·

    Wonyoung Kim

    DBLP profile ↗ORCID search ↗
13. Minimax Optimal Reinforcement Learning with Quasi-Optimism
    ICLR 2025 ·

    Harin Lee

    DBLP profile ↗ORCID search ↗
14. Optimal and Practical Batched Linear Bandit Algorithm
    ICML 2025 ·

    Sanghoon Yu

    DBLP profile ↗ORCID search ↗
15. Oracle-Efficient Combinatorial Semi-Bandits
    NeurIPS 2025 ·

    Jung-hun Kim

    DBLP profile ↗ORCID search ↗
16. Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift
    NeurIPS 2025 ·

    Eunsu Baek

    DBLP profile ↗ORCID search ↗
17. Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
    NeurIPS 2025 ·

    Joongkyu Lee

    DBLP profile ↗ORCID search ↗
18. Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
    NeurIPS 2025 ·

    Jongyeong Lee

    DBLP profile ↗ORCID search ↗
19. Symmetry-Aware GFlowNets
    ICML 2025 ·

    Hohyun Kim

    DBLP profile ↗ORCID search ↗
20. Thompson Sampling for Multi-Objective Linear Contextual Bandit
    NeurIPS 2025 ·

    Somangchan Park

    DBLP profile ↗ORCID search ↗
21. Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
    NeurIPS 2025 ·

    Taehyun Hwang

    DBLP profile ↗ORCID search ↗
22. True Impact of Cascade Length in Contextual Cascading Bandits
    NeurIPS 2025 ·

    Hyun-jun Choi

    DBLP profile ↗ORCID search ↗
23. Demystifying Linear MDPs and Novel Dynamics Aggregation Framework
    ICLR 2024 ·

    Joongkyu Lee

    DBLP profile ↗ORCID search ↗
24. Doubly Perturbed Task Free Continual Learning
    AAAI 2024 ·

    Byung Hyun Lee

    DBLP profile ↗ORCID search ↗
25. Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
    COLT 2024 ·

    Jongyeong Lee

    DBLP profile ↗ORCID search ↗
26. Improved Regret of Linear Ensemble Sampling
    NeurIPS 2024 ·

    Harin Lee

    DBLP profile ↗ORCID search ↗
27. Learning Uncertainty-Aware Temporally-Extended Actions
    AAAI 2024 ·

    Joongkyu Lee

    DBLP profile ↗ORCID search ↗
28. Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
    NeurIPS 2024 ·

    Seok-Jin Kim

    DBLP profile ↗ORCID search ↗
29. Mixed-Effects Contextual Bandits
    AAAI 2024 ·

    Kyungbok Lee

    DBLP profile ↗ORCID search ↗
30. Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
    NeurIPS 2024 ·

    Joongkyu Lee

    DBLP profile ↗ORCID search ↗
31. Queueing Matching Bandits with Preference Feedback
    NeurIPS 2024 ·

    Jung-hun Kim

    DBLP profile ↗ORCID search ↗
32. Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
    NeurIPS 2024 ·

    Wooseong Cho

    DBLP profile ↗ORCID search ↗