mlsanityData to 14 Oct 2026

On Architectures for Combining Reinforcement Learning and Model Predictive Control with Runtime Improvements

arXiv 2510.03354 ↗First posted 2 Oct 2025eess.SY cs.SYcited by 0

On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic

Abstract (arXiv)

Model Predictive Control (MPC) faces computational demands and performance degradation from model inaccuracies. We propose two architectures combining Neural Network-approximated MPC (NNMPC) with Reinforcement Learning (RL). The first, Warm Start RL, initializes the RL actor with pre-trained NNMPC weights. The second, RLMPC, uses RL to generate corrective residuals for NNMPC outputs. We introduce a downsampling method reducing NNMPC input dimensions while maintaining performance. Evaluated on a rotary inverted pendulum, both architectures demonstrate runtime reductions exceeding 99% compared to traditional MPC while improving tracking performance under model uncertainties, with RL+MPC achieving 11-40% cost reduction depending on reference amplitude.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 8 of its 20 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

8 of 20 references.

References · 8

  1. 2015Continuous control with deep reinforcement learningcited by 3,407
  2. 2019Safe Reinforcement Learning Using Robust MPCcited by 85
  3. 2018Efficient representation and approximation of model predictive control laws via deep learningcited by 58
  4. 2020Learning for MPC with Stability & Safety Guaranteescited by 14
  5. 2018Recurrent Neural Network-based Model Predictive Control for Continuous Pharmaceutical Manufacturingcited by 9
  6. 2024Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programmingcited by 7
  7. 2018Adaptive MPC for Autonomous Lane Keepingcited by 2
  8. 2023Robust Tracking Control for Nonlinear Systems: Performance optimization via extremum seekingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MPCritic: A plug-and-play MPC architecture for reinforcement learning
  2. 2025Residual MPC: Blending Reinforcement Learning with GPU-Parallelized Model Predictive Control
  3. 2024AC4MPC: Actor-Critic Reinforcement Learning for Nonlinear Model Predictive Control
  4. 2026A Systematic Review and Taxonomy of Reinforcement Learning-Model Predictive Control Integration for Linear Systems
  5. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification
  6. 2018Differentiable MPC for End-to-end Planning and Control
  7. 2026Soft MPCritic: Value-Based Reinforcement Learning for Non-Differentiable Predictive Control
  8. 2024Faster Model Predictive Control via Self-Supervised Initialization Learning