mrana6 / euclideanizing_flows

Stable dynamical system learning using Euclideanizing flows

SDSEF: Stable Dynamical System Learning Using Euclideanizing Flows

SDSEF is a dynamical system or policy learning approach with global asymptotic stability guarantees. For details, checkout our publication in L4DC 2020.

This library is an implementation of SDSEF in pytorch.

SDSEF is being developed by Asif Rana and Anqi Li.

Prerequisites

• python >= 2.7
• PyTorch >= 1.5.0
• numpy
• matplotlib
• scipy

Citing

If you use SDSEF in an academic context, please cite the following publication:

[1]
@article{rana2020euclideanizing,
  title={Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems},
  author={Rana, Muhammad Asif and Li, Anqi and Fox, Dieter and Boots, Byron and Ramos, Fabio and Ratliff, Nathan},
  journal={2nd Conference on Learning from Dynamics and Control (L4DC)},
  year={2020}
}

Questions & Bug reporting

Please use Github issue tracker to report bugs. For other questions, please contact Asif Rana or Anqi Li.

License

SDSEF is released under the MIT license, reproduced in the file LICENSE in this directory.