Showing eess.SYShow all
2 papers · 1 filter
eess.SY2025
Off Policy Lyapunov Stability in Reinforcement Learning
Sarvan Gill, Daniela Constantinescu
Traditional reinforcement learning lacks the ability to provide stability guarantees. More recent algorithms learn Lyapunov functions alongside the control policies to ensure stabl…
eess.SY2019
Connectivity-Preserving Swarm Teleoperation Over A Tree Network With Time-Varying Delays
Yuan Yang, Yang Shi, Daniela Constantinescu
A teleoperated swarm must follow the unpredictable commands of its human operator while remaining connected. When the swarm communications are limited by distance and affected by d…