mlsanityData to 14 Oct 2026

A Model-Free Optimal Control Method With Fixed Terminal States and Delay

arXiv 2409.10722 ↗First posted 16 Sep 2024eess.SY cs.SYcited by 0

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

Model-free algorithms are brought into the control system's research with the emergence of reinforcement learning algorithms. However, there are two practical challenges of reinforcement learning-based methods. First, learning by interacting with the environment is highly complex. Second, constraints on the states (boundary conditions) require additional care since the state trajectory is implicitly defined from the inputs and system dynamics. To address these problems, this paper proposes a new model-free algorithm based on basis functions, gradient estimation, and the Lagrange method. The favorable performance of the proposed algorithm is shown using several examples under state-dependent switches and time delays.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 4 of its 25 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

4 of 25 references.

References · 4

  1. 2018Reward Constrained Policy Optimizationcited by 417
  2. 2020A Convex Approach to Data-driven Optimal Control via Perron-Frobenius and Koopman Operatorscited by 1
  3. 2022NOSNOC: A Software Package for Numerical Optimal Control of Nonsmooth Systemscited by 1
  4. 2022Jump Law of Co-State in Optimal Control for State-Dependent Switched Systems and Applicationscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Data-Driven Inverse Optimal Control for Continuous-Time Nonlinear Systems
  2. 2024Guiding Reinforcement Learning with Incomplete System Dynamics
  3. 2026Model-Free Q-Learning for Infinite-Horizon Stochastic Linear Quadratic Problems with Regime Switching
  4. 2026Model-free policy gradient for discrete-time mean-field control
  5. 2026Model-Free Output Feedback Stabilization via Policy Gradient Methods
  6. 2024Model-free optimal controller for discrete-time Markovian jump linear systems: A Q-learning approach
  7. 2025On the Robustness of Derivative-free Methods for Linear Quadratic Regulator
  8. 2026Model-Based Data-Efficient and Robust Reinforcement Learning