Reinforcement learning based constrained optimal control: an interpretable reward design

DOI10.1016/J.AUTOMATICA.2026.112995MaRDI QIDQ7302600zbMATH OpenFDO

Authors Jingjie Ni, Fangfei Li, Xin Jin, Xianlun Peng, Yang Tang

Publication date 22 July 2026

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2026.112995

Mathematics Subject Classification ID

Calculus of variations and optimal control; optimization (49-XX) Model systems in control theory (93Cxx)

Cites work

• An exact penalty method for free terminal time optimal control problem with continuous inequality constraints
• Cluster-based distributed augmented Lagrangian algorithm for a class of constrained convex optimization problems
• Dealing with infeasibility in multi-parametric programming for application to explicit model predictive control
• Discrete Time Pontryagin Maximum Principle Under State-Action-Frequency Constraints
• Distributed entropy-regularized multi-agent reinforcement learning with policy consensus
• Exact penalty functions for optimal control problems. II: Exact penalization of terminal and pointwise state constraints
• Optimal control
• Reinforcement learning control of constrained dynamic systems with uniformly ultimate boundedness stability guarantee
• Reinforcement learning. An introduction
• Safe Value Functions

This page was built for publication: Reinforcement learning based constrained optimal control: an interpretable reward design

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7302600)