Near Optimal Hamiltonian-Control and Learning via Chattering

2017/03/19 by Peeyush Kumar, Kumar, Peeyush, Wolf Kohn +3
Computer Science · Engineering · #Adaptive Dynamic Programming Control #Advanced Control Systems Optimization #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #cs.LG

paper · pdf · doi:10.48550/arxiv.1703.06485

arxiv created 2017/03/19 · openalex publication_date 2017/03/19 · arxiv updated 2017/03/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Many applications require solving non-linear control problems that are classically not well behaved. This paper develops a simple and efficient chattering algorithm that learns near optimal decision policies through an open-loop feedback strategy. The optimal control problem reduces to a series of linear optimization programs that can be easily solved to recover a relaxed optimal trajectory. This algorithm is implemented on a real-time enterprise scheduling and control process.

Related

• Regularization of chattering phenomena via bounded variation control
• Data-driven Dynamic Multi-objective Optimal Control: An Aspiration-satisfying Reinforcement Learning Approach
• Neural Co-state Regulator: A Data-Driven Paradigm for Real-time Optimal Control with Input Constraints
• Learning Optimal Feedback Operators and their Polynomial Approximation
• A Nearly Optimal Chattering Reduction Method of Sliding Mode Control With an Application to a Two-wheeled Mobile Robot