mlsanityData to 7 Oct 2026

MPC-Net: A First Principles Guided Policy Search

arXiv 1909.05197 ↗First posted 11 Sep 2019cs.RO cs.LGcited by 28

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

We present an Imitation Learning approach for the control of dynamical systems with a known model. Our policy search method is guided by solutions from MPC. Typical policy search methods of this kind minimize a distance metric between the guiding demonstrations and the learned policy. Our loss function, however, corresponds to the minimization of the control Hamiltonian, which derives from the principle of optimality. Therefore, our algorithm directly attempts to solve the optimality conditions with a parameterized class of control laws. Additionally, the proposed loss function explicitly encodes the constraints of the optimal control problem and we provide numerical evidence that its minimization achieves improved constraint satisfaction. We train a mixture-of-expert neural network architecture for controlling a quadrupedal robot and show that this policy structure is well suited for such multimodal systems. The learned policy can successfully stabilize different gaits on the real walking robot from less than 10 min of demonstration data.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. First posted on arXiv 11 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 5; 2023: 4; 2024: 3; 2025: 4; 2026: 4.

28 papers.

Sort:

By area:

  1. 2021Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overviewcited by 42
  2. 2022Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviorscited by 27
  3. 2021GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Modelcited by 23
  4. 2022Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controllercited by 23
  5. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 19
  6. 2021Imitation Learning from MPC for Quadrupedal Multi-Gait Controlcited by 16
  7. 2021Evaluating model-based planning and planner amortization for continuous controlcited by 15
  8. 2021Learning-based Robust Motion Planning with Guaranteed Stability: A Contraction Theory Approachcited by 13
  9. 2021Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPCcited by 10
  10. 2023Approximate non-linear model predictive control with safety-augmented neural networkscited by 9
  11. 2024Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllerscited by 9
  12. 2024Planning-Guided Diffusion Policy Learning for Generalizable Contact-Rich Bimanual Manipulationcited by 8
16 more
  1. 2022Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environmentscited by 7
  2. 2024Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retrainingcited by 6
  3. 2021Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Plannercited by 4
  4. 2023Imitation Learning from Nonlinear MPC via the Exact Q-Loss and its Gauss-Newton Approximationcited by 4
  5. 2025The Mini Wheelbot: A Testbed for Learning-based Balancing, Flips, and Articulated Drivingcited by 4
  6. 2022Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible Robotscited by 3
  7. 2025Diffusion-Based Approximate MPC: Fast and Consistent Imitation of Multi-Modal Action Distributionscited by 3
  8. 2025Generative Models From and For Sampling-Based MPC: A Bootstrapped Approach For Adaptive Contact-Rich Manipulationcited by 2
  9. 2023Integrating Expert Guidance for Efficient Learning of Safe Overtaking in Autonomous Driving Using Deep Reinforcement Learningcited by 1
  10. 2021Generalized Reinforcement Learning for Building Control using Behavioral Cloningcited by 0
  11. 2022Knowledge-Integrated Informed AI for National Securitycited by 0
  12. 2023Efficient Deep Learning of Robust, Adaptive Policies using Tube MPC-Guided Data Augmentationcited by 0
  13. 2026Neuro-Inspired Inverse Learning for Planning and Controlcited by 0
  14. 2026Amortising Trajectory Optimisation for Residual MPC via Implicit Contact Differentiationcited by 0
  15. 2026Guided Riemannian Optimization (GuRO): Bridging Model Predictive Control and Decision Transformerscited by 0
  16. 2026SUN: Agentic Robot Policy Learning with Persistent Task Programscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2019Learning the optimal state-feedback via supervised imitation learning
  2. 2021MPC-MPNet: Model-Predictive Motion Planning Networks for Fast, Near-Optimal Planning under Kinodynamic Constraints
  3. 2026Learning Quadruped Walking from Seconds of Demonstration
  4. 2019Formal Policy Learning from Demonstrations for Reachability Properties
  5. 2023GAN-MPC: Training Model Predictive Controllers with Parameterized Cost Functions using Demonstrations from Non-identical Experts
  6. 2026GCImOpt: Learning efficient goal-conditioned policies by imitating optimal trajectories
  7. 2018Differentiable MPC for End-to-end Planning and Control
  8. 2024PlanNetX: Learning an Efficient Neural Network Planner from MPC for Longitudinal Control