3 papers
cs.AI2024
Safe and Reliable Training of Learning-Based Aerospace Controllers
Udayan Mandal, Guy Amir, Haoze Wu +10
In recent years, deep reinforcement learning (DRL) approaches have generated highly successful controllers for a myriad of complex domains. However, the opaque nature of these mode…
cs.AI2024
Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates
Udayan Mandal, Guy Amir, Haoze Wu +9
Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating agents that control autonomous systems. However, the ``black box'' nature of DRL agents lim…
math.OC2024
A New Class of Compact Formulations for Vehicle Routing Problems
Udayan Mandal, Amelia Regan, Louis Martin Rousseau +1
This paper introduces a novel compact mixed integer linear programming (MILP) formulation and a discretization discovery-based solution approach for the Vehicle Routing Problem wit…