Litcius/Paper detail

Discrete-Time Nonlinear Optimal Control Using Multi-Step Reinforcement Learning

Ningbo An, Qishao Wang, Xiaochuan Zhao, Qingyun Wang

2023IEEE Transactions on Circuits & Systems II Express Briefs12 citationsDOI

Abstract

This paper solves the optimal control problem of discrete-time nonlinear systems by proposing a multi-step reinforcement learning (RL) algorithm. The proposed multi-step RL algorithm is established based on the discrete-time optimal Bellman equation, which takes advantage of policy iteration (PI) and value iteration (VI). Benefiting from the multi-step integration mechanism, the algorithm is accelerated. The convergence of multi-step RL is proved by mathematical induction. For real-world implementation purposes, neural network (NN) and Actor-Critic architecture are introduced to approximate the iterative value functions and control policies. A numerical simulation of Chua’s circuit illustrates the effectiveness of the proposed algorithm.

Topics & Concepts

Reinforcement learningConvergence (economics)Computer scienceNonlinear systemOptimal controlDiscrete time and continuous timeArtificial neural networkBellman equationMathematical optimizationHamilton–Jacobi–Bellman equationControl theory (sociology)Control (management)AlgorithmMathematicsArtificial intelligenceQuantum mechanicsEconomicsPhysicsStatisticsEconomic growthAdaptive Dynamic Programming ControlReinforcement Learning in RoboticsAdaptive Control of Nonlinear Systems
Discrete-Time Nonlinear Optimal Control Using Multi-Step Reinforcement Learning | Litcius