A reinforcement learning approach to hybrid control design

2020/09/02 by Meet Gandhi, Atreyee Kundu, Gandhi, Meet +3
Computer Science · Engineering · #Adaptive Dynamic Programming Control #Artificial Intelligence (cs.AI) #Electric Vehicles and Infrastructure #FOS: Computer and information sciences #FOS: Electrical engineering #Reinforcement Learning in Robotics #Systems and Control (eess.SY) #cs.AI #cs.SY #eess.SY #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2009.00821

9 pages

arxiv created 2020/09/02 · openalex publication_date 2020/09/02 · arxiv updated 2020/09/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this paper we design hybrid control policies for hybrid systems whose mathematical models are unknown. Our contributions are threefold. First, we propose a framework for modelling the hybrid control design problem as a single Markov Decision Process (MDP). This result facilitates the application of off-the-shelf algorithms from Reinforcement Learning (RL) literature towards designing optimal control policies. Second, we model a set of benchmark examples of hybrid control design problem in the proposed MDP framework. Third, we adapt the recently proposed Proximal Policy Optimisation (PPO) algorithm for the hybrid action space and apply it to the above set of problems. It is observed that in each case the algorithm converges and finds the optimal policy.

Related

• A General Markov Decision Process Framework for Directly Learning Optimal Control Policies
• Control as Hybrid Inference
• Control and Reinforcement Learning through the Lens of Optimization: An Algorithmic Perspective
• Linear Dynamics meets Linear MDPs: Closed-Form Optimal Policies via Reinforcement Learning
• Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification