collaborators

6 papers

cs.RO2026

Natural Gradient Bayesian Filtering: Geometry-Aware Filter for Dynamical Systems

Chang Liu, Wenhan Cao, Zeju Sun +8

Bayesian filtering is a cornerstone of state estimation in complex systems such as aerospace systems, yet exact solutions are available only for linear Gaussian models. In practice…

cs.LG2026

Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning

Jiaming Zhang, Yujie Yang, Yao Lyu +2

Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominent paradigm. Handling state-w…

cs.LG2026

A Spectral Revisit of the Distributional Bellman Operator under the Cramér Metric

Keru Wang, Yixin Deng, Yao Lyu +2

Distributional reinforcement learning (DRL) studies the evolution of full return distributions under Bellman updates rather than focusing on expected values. A classical result is…

cs.LG2026

Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation

Guojian Zhan, Letian Tao, Pengcheng Wang +6

Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling com…

cs.LG2026

Real-Time Generative Policy via Langevin-Guided Flow Matching for Autonomous Driving

Tianze Zhu, Yinuo Wang, Wenjun Zou +6

Reinforcement learning (RL) is a fundamental methodology in autonomous driving systems, where generative policies exhibit considerable potential by leveraging their ability to mode…

cs.LG2025

Bootstrap Off-policy with World Model

Guojian Zhan, Likun Wang, Xiangteng Zhang +3

Online planning has proven effective in reinforcement learning (RL) for improving sample efficiency and final performance. However, using planning for environment interaction inevi…