mlsanityData to 14 Oct 2026

Reservoir Predictive Path Integral Control for Unknown Nonlinear Dynamics

arXiv 2509.03839 ↗First posted 4 Sep 2025eess.SY cs.LG cs.SYcited by 1

Not on the map. Why?

Abstract (arXiv)

Neural networks have found extensive application in data-driven control of nonlinear dynamical systems, yet fast online identification and control of unknown dynamics remain central challenges. To meet these challenges, this paper integrates echo-state networks (ESNs)--reservoir computing models implemented with recurrent neural networks--and model predictive path integral (MPPI) control--sampling-based variants of model predictive control. The proposed reservoir predictive path integral (RPPI) enables fast learning of nonlinear dynamics with ESNs and exploits the learned nonlinearities directly in MPPI control computation without linearization approximations. This framework is further extended to uncertainty-aware RPPI (URPPI), which achieves robust stochastic control by treating ESN output weights as random variables and minimizing an expected cost over their distribution to account for identification errors. Experiments on controlling a Duffing oscillator and a four-tank system demonstrate that URPPI improves control performance, reducing control costs by up to 60% compared to traditional quadratic programming-based model predictive control methods.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 54 references that are in the map. First posted on arXiv 4 Sep 2025.

Builds on

14 of 54 references.

References · 14

  1. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  2. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  3. 2018Graph networks as learnable physics engines for inference and controlcited by 244
  4. 2017OSQP: An Operator Splitting Solver for Quadratic Programscited by 161
  5. 2015Model Predictive Path Integral Control using Covariance Variable Importance Samplingcited by 124
  6. 2017Information Theoretic Model Predictive Control: Theory and Applications to Autonomous Drivingcited by 90
  7. 2018Optimal Control Via Neural Networks: A Convex Approachcited by 85
  8. 2022Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platformscited by 41
  9. 2022JuMP 1.0: Recent improvements to a modeling language for mathematical optimizationcited by 37
  10. 2021Nonlinear MPC for Offset-Free Tracking of systems learned by GRU Neural Networkscited by 11
  11. 2022Risk-Aware Model Predictive Path Integral Control Using Conditional Value-at-Riskcited by 5
  12. 2023Recent Advances in Path Integral Control for Trajectory Optimization: An Overview in Theoretical and Algorithmic Perspectivescited by 5
2 more
  1. 2024Fast Explicit Machine Learning-Based Model Predictive Control of Nonlinear Processes Using Input Convex Neural Networkscited by 4
  2. 2016Gaussian Process Model Predictive Control of Unknown Nonlinear Systemscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026LoRA-RC: Reservoir Computing with Low-Rank Adaptationcited by 0