Corpus ID: 211296627

Neural Lyapunov Model Predictive Control

@article{Mittal2020NeuralLM,
  title={Neural Lyapunov Model Predictive Control},
  author={Mayank K. Mittal and Marco Gallieri and A. Quaglino and Seyed Sina Mirrazavi Salehian and Jan Koutn'ik},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.10451}
}
This paper presents Neural Lyapunov MPC, an algorithm to alternately train a Lyapunov neural network and a stabilising constrained Model Predictive Controller (MPC), given a neural network model of the system dynamics. This extends recent works on Lyapunov networks to be able to train solely from expert demonstrations of one-step transitions. The learned Lyapunov network is used as the value function for the MPC in order to guarantee stability and extend the stable region. Formal results are… Expand
Learning Safe Neural Network Controllers with Barrier Certificates
Formal Synthesis of Lyapunov Neural Networks

References

SHOWING 1-10 OF 76 REFERENCES
Infinite-Horizon Differentiable Model Predictive Control
Neural Lyapunov Control
Differentiable MPC for End-to-end Planning and Control
Safe Model-based Reinforcement Learning with Stability Guarantees
Constrained model predictive control: Stability and optimality
The explicit solution of model predictive control via multiparametric quadratic programming
Model Predictive Control: Classical, Robust and Stochastic
Stability of infinite-horizon optimal control with discounted cost
...
1
2
3
4
5
...