Kim, Seonghyun

8 publications

NeurIPSW 2024 Efficient Fine-Tuning of Behavior Cloned Policies with Reinforcement Learning from Limited Demonstrations Samyeul Noh, Seonghyun Kim, Ingook Jang

NeurIPSW 2024 Online Fine-Tuning with Uncertainty Quantification for Offline Pre-Trained Agents Ingook Jang, Seonghyun Kim, Samyeul Noh

WACV 2024 Robust Unsupervised Domain Adaptation Through Negative-View Regularization Joonhyeok Jang, Sunhyeok Lee, Seonghak Kim, Jung-un Kim, Seonghyun Kim, Daeshik Kim

NeurIPSW 2023 An Investigation into Value-Implicit Pre-Training for Task-Agnostic, Sample-Efficient Goal-Conditioned Reinforcement Learning Samyeul Noh, Seonghyun Kim, Ingook Jang, Hyun Myung

NeurIPSW 2023 Numerical Goal-Based Transformers for Practical Conditions Seonghyun Kim, Samyeul Noh, Ingook Jang

NeurIPSW 2022 Uncertainty-Driven Pessimistic Q-Ensemble for Offline-to-Online Reinforcement Learning Ingook Jang, Seonghyun Kim

CoRL 2021 Stochastic Policy Optimization with Heuristic Information for Robot Learning Seonghyun Kim, Ingook Jang, Samyeul Noh, Hyunseok Kim

NeurIPSW 2021 Stochastic Video Prediction with Perceptual Loss Donghun Lee, Ingook Jang, Seonghyun Kim, Chanwon Park, Junhee Park