Seungyub Han

Publication Activity (10 Years)

Years Active: 2023-2024
Publications (10 Years): 9

Top Topics

Function Approximation

Reinforcement Learning

Convergence Proof

Top Venues

Publications

Dohyeok Lee, Seungyub Han, Taehyun Cho, Jungwoo Lee
SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning. CoRR (2024)
Seungyub Han, Yeongmo Kim, Taehyun Cho, Jungwoo Lee
On the Convergence of Continual Learning with Adaptive Methods. CoRR (2024)
Dohyeong Kim, Taehyun Cho, Seungyub Han, Hojun Chung, Kyungjae Lee, Songhwai Oh
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees. CoRR (2024)
Taehyun Cho, Seungyub Han, Kyungjae Lee, Seokhun Ju, Dohyeong Kim, Jungwoo Lee
Tractable and Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation. CoRR (2024)
Taehyun Cho, Seungyub Han, Heesoo Lee, Kyungjae Lee, Jungwoo Lee
Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion. CoRR (2023)
Taehyun Cho, Seungyub Han, Heesoo Lee, Kyungjae Lee, Jungwoo Lee
Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion. NeurIPS (2023)
Seungyub Han, Yeongmo Kim, Taehyun Cho, Jungwoo Lee
On the Convergence of Continual Learning with Adaptive Methods. UAI (2023)
Dohyeok Lee, Seungyub Han, Taehyun Cho, Jungwoo Lee
SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning. NeurIPS (2023)
Seungyub Han, Yeongmo Kim, Seokhyeon Ha, Jungwoo Lee, Seunghong Choi
Learning to Learn Unlearned Feature for Brain Tumor Segmentation. CoRR (2023)