From the 1 of 6 linked papers with an AI index.
6 papers
Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration
Zeyang Li, Chuxiong Hu, Yunan Wang +4
The paper shows that regularized policy iteration in reinforcement learning is mathematically equivalent to applying the Newton‑Raphson method to a smoothed Bellman equation, provi…
DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
Paolo Giaretta, Zeyang Li, Navid Azizan
Diffusion models have emerged as powerful tools for planning and control by learning multimodal distributions over actions and trajectories. Yet reliable inference-time safety enfo…
From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning
Ranxu zhang, zeyang li, Jiacheng Huang +5
Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned b…
Reachability-Augmented Dual Dynamic Programming for Optimal Path Parameterization
Yunan Wang, Jizhou Yan, Chuxiong Hu +1
Optimal path parameterization (OPP) is a fundamental problem for planning trajectories along a prescribed geometric path under kinodynamic constraints and task-dependent objectives…
A Novel State-Centric Necessary Condition for Time-Optimal Control of Controllable Linear Systems Based on Augmented Switching Laws (Extended Version)
Yunan Wang, Chuxiong Hu, Yujie Lin +3
Most existing necessary conditions for optimal control based on adjoining methods require both state and costate information, yet the unobservability of costates for a given feasib…
Chattering Phenomena in Time-Optimal Control for High-Order Chain-of-Integrator Systems with Full State Constraints (Extended Version)
Yunan Wang, Chuxiong Hu, Zeyang Li +3
Time-optimal control for high-order chain-of-integrator systems with full state constraints remains an open and challenging problem within the discipline of optimal control. The be…