1 citations · 1 across the 6 of their papers we have counts for
7 papers
Natural Functional Gradients for Smooth Trajectory Optimization
Kisang Park, Chanwoo Kim, Kyungjae Lee +1
Generating collision-free and smooth motions remains a central challenge in robotic manipulation, particularly in cluttered environments and narrow passages where feasible regions…
Probabilistic Smoothing with Ratio-Monotone Transforms for Global Optimization
Kukyoung Jang, Taehyun Cho, Junrui Zhang +2
Probabilistic smoothing is a standard tool for global optimization, but existing methods rely on Gaussian kernels and specific transforms, often resulting in strong hyperparameter…
Learning Robust Visuomotor Policies via Dynamics Alignment
Dohyeok Lee, Jung Min Lee, Munkyung Kim +8
Generative BC policies model expert action distributions well, but they do not explicitly reason about what scene a candidate action would produce, so they cannot tell whether it r…
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…
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Dohyeong Kim, Taehyun Cho, Seungyub Han +3
The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-base…
Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion
Taehyun Cho, Seungyub Han, Heesoo Lee +2
Distributional reinforcement learning algorithms have attempted to utilize estimated uncertainty for exploration, such as optimism in the face of uncertainty. However, using the es…