no code implementations • 8 Mar 2024 • Jongyeong Lee, Junya Honda, Shinji Ito, Min-hwan Oh
In this paper, we establish a sufficient condition for perturbations to achieve $\mathcal{O}(\sqrt{KT})$ regrets in the adversarial setting, which covers, e. g., Fr\'{e}chet, Pareto, and Student-$t$ distributions.
no code implementations • 8 Feb 2024 • Joongkyu Lee, Seung Joon Park, Yunhao Tang, Min-hwan Oh
In reinforcement learning, temporal abstraction in the action space, exemplified by action repetition, is a technique to facilitate policy learning through extended actions.
no code implementations • 20 Dec 2023 • Byung Hyun Lee, Min-hwan Oh, Se Young Chun
Specifically, for input perturbation, we propose an approximate perturbation method that injects noise into the input data as well as the feature vector and then interpolates the two perturbed samples.
1 code implementation • 21 Jul 2023 • Byeongchan Kim, Min-hwan Oh
In this paper, we propose a model-based offline reinforcement learning method that integrates count-based conservatism, named $\texttt{Count-MORL}$.
no code implementations • 31 May 2023 • TaeHyun Hwang, Kyuwook Chai, Min-hwan Oh
Approximating this unknown score function with deep neural networks, we propose algorithms: Combinatorial Neural UCB ($\texttt{CN-UCB}$) and Combinatorial Neural Thompson Sampling ($\texttt{CN-TS}$).
no code implementations • 27 Dec 2022 • TaeHyun Hwang, Min-hwan Oh
In this paper, we establish a provably efficient RL algorithm for the MDP whose state transition is given by a multinomial logistic model.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 11 Jun 2022 • Wonyoung Kim, Myunghee Cho Paik, Min-hwan Oh
We propose a linear contextual bandit algorithm with $O(\sqrt{dT\log T})$ regret bound, where $d$ is the dimension of contexts and $T$ isthe time horizon.
1 code implementation • 23 May 2022 • Jaehun Song, Min-hwan Oh, Hyung-Sin Kim
Personalized Federated Learning (FL) is an emerging research field in FL that learns an easily adaptable global model in the presence of data heterogeneity among clients.
no code implementations • 25 Mar 2021 • Min-hwan Oh, Garud Iyengar
We propose upper confidence bound based algorithms for this MNL contextual bandit.
1 code implementation • 16 Jul 2020 • Min-hwan Oh, Garud Iyengar, Assaf Zeevi
We consider a stochastic contextual bandit problem where the dimension $d$ of the feature vectors is potentially large, however, only a sparse subset of features of cardinality $s_0 \ll d$ affect the reward function.
no code implementations • 22 Apr 2020 • Min-hwan Oh, Garud Iyengar
In order to construct a reliable anomaly detection method and take into consideration the confidence of the predicted anomaly score, we adopt a Bayesian approach for IRL.
1 code implementation • NeurIPS 2019 • Min-hwan Oh, Garud Iyengar
The feedback here is the item that the user picks from the assortment.
no code implementations • 30 May 2019 • Min-hwan Oh, Peder Olsen, Karthikeyan Natesan Ramamurthy
We also propose a novel instance segmentation algorithm using the estimated density map, to identify the individual panicles in the presence of occlusion.
no code implementations • 15 Mar 2019 • Min-hwan Oh, Peder A. Olsen, Karthikeyan Natesan Ramamurthy
Uncertainty quantification accompanied by point estimation can lead to a more informed decision, and even improve the prediction quality.
1 code implementation • 21 Dec 2018 • Hiroki Kanezashi, Toyotaro Suzumura, Dario Garcia-Gasulla, Min-hwan Oh, Satoshi Matsuoka
We propose an incremental graph pattern matching algorithm to deal with time-evolving graph data and also propose an adaptive optimization system based on reinforcement learning to recompute vertices in the incremental process more efficiently.
Databases
no code implementations • 31 Aug 2018 • Min-hwan Oh, Garud Iyengar
We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead.
no code implementations • ICLR 2018 • Weiyi Liu, Hal Cooper, Min-hwan Oh
Inspired by the success of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via GANs.