4 papers
MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction
Jung Min Lee, Dohyeok Lee, Seokhun Ju +5
Latent actions learned from diverse human videos serve as pseudo-labels for vision-language-action (VLA) pretraining, but provide effective supervision only if they remain informat…
Learning Generalizable Visuomotor Policy through Dynamics-Alignment
Dohyeok Lee, Jung Min Lee, Munkyung Kim +6
Behavior cloning methods for robot learning suffer from poor generalization due to limited data support beyond expert demonstrations. Recent approaches leveraging video prediction…
Policy-labeled Preference Learning: Is Preference Enough for RLHF?
Taehyun Cho, Seokhun Ju, Seungyub Han +3
To design rewards that align with human goals, Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent technique for learning reward functions from human prefe…
Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation
Taehyun Cho, Seungyub Han, Seokhun Ju +3
Distributional reinforcement learning improves performance by capturing environmental stochasticity, but a comprehensive theoretical understanding of its effectiveness remains elus…