Seungyub Han
6 papers · 2023–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Silver
๐บ๏ธ
Taxonomy Completionist
(13)
โ
The Questioner
Venues
Top co-authors
Research topics
Keywords
deep reinforcement learning
(1)
reinforcement learning
(1)
continual learning
(1)
catastrophic forgetting
(1)
offline reinforcement learning
(1)
non-convex optimization
(1)
policy optimization
(1)
direct preference optimization
(1)
distributional reinforcement learning
(1)
continuous control
(1)
sequential learning
(1)
variance estimation
(1)
optimistic exploration
(1)
eluder dimension
(1)
bilevel optimization
(1)
random matrix theory
(1)
regret bound
(1)
convergence guarantee
(1)
ensemble method
(1)
atari game
(1)
Papers
Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation
ICML 2025
Policy-labeled Preference Learning: Is Preference Enough for RLHF?
ICML 2025
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
NeurIPS 2024
On the Convergence of Continual Learning with Adaptive Methods
UAI 2023
Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion
NeurIPS 2023
SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning
NeurIPS 2023