5 papers
Safe Online Learning via Smooth Safety-Structured Policy Composition
Hongpeng Cao, Liqun Zhao, Yuliang Gu +3
Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics. Existing approaches typically rely on either stri…
Constrained Diffusers for Safe Planning and Control
Jichen Zhang, Liqun Zhao, Antonis Papachristodoulou +1
Diffusion models have shown remarkable potential in planning and control tasks due to their ability to represent multimodal distributions over actions and trajectories. However, en…
Opt-ODENet: A Neural ODE Framework with Differentiable QP Layers for Safe and Stable Control Design (longer version)
Keyan Miao, Liqun Zhao, Han Wang +2
Designing controllers that achieve task objectives while ensuring safety is a key challenge in control systems. This work introduces Opt-ODENet, a Neural ODE framework with a diffe…
Data-Driven Stable Neural Feedback Loop Design
Zuxun Xiong, Han Wang, Liqun Zhao +1
This paper proposes a data-driven approach to design a feedforward Neural Network (NN) controller with a stability guarantee for plants with unknown dynamics. We first introduce da…
Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations
Liqun Zhao, Keyan Miao, Konstantinos Gatsis +1
Reinforcement learning (RL) excels in applications such as video games, but ensuring safety as well as the ability to achieve the specified goals remains challenging when using RL…