Code for "SINDy-RL for Interpretable and Efficient Model-Based Reinforcement Learning" by Zolman et al.
-
Updated
Mar 28, 2026 - Python
Code for "SINDy-RL for Interpretable and Efficient Model-Based Reinforcement Learning" by Zolman et al.
Scripts and notebooks to accompany the book Data-Driven Methods for Dynamic Systems
AutoKoopman - automated Koopman operator methods for data-driven dynamical systems analysis and control.
a collection of modern sparse (regularized) linear regression algorithms.
Example code for paper: Automatic Differentiation to Simultaneously Identify Nonlinear Dynamics and Extract Noise Probability Distributions from Data
Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants. Proceedings of the Royal Society A.
Physically-informed model discovery of systems with nonlinear, rational terms using the SINDy-PI method. Contains functionality for spectral filtering/differentiation.
MEDIDA: Model Error Discovery with Interpretability and Data Assimilation
Sparse Identification of Nonlinear Dynamics (SINDy, E-SINDy & weak-SINDy) built from scratch, test-first — discover governing ODEs from data.
From a raw optical-sensor signal to interpretable physics: signal processing, system identification (SINDy/HAVOK/PINN) and Euler-Bernoulli beam modeling.
mSINDy is a modular MATLAB framework for sparse identification of nonlinear dynamical systems from data. The repository provides tools for equation discovery, sparse regression, candidate-library construction, model validation, and data-driven analysis of linear, nonlinear, and chaotic dynamics using SINDy methodologies.
A data-driven pipeline for modeling and predicting 2D vector field dynamics using dimensionality reduction and multiple forecasting methods. (ME5311 Project 2)
Weak Identification of Analytic Systems
Building SINDy model from scratch
Lorenz 63 Attractor, Kortweg - De Vries and Burgers equations, and wave stuff.
Hybrid kinetic models for small biochemical networks: learn the unknown rate laws from time-series data, then recover them symbolically
JAX-accelerated parametric SINDy grid search with batched sparse regression and reduced-order rollouts.
Выпускная квалификационная работа бакалавра
To associate your repository with the sindy topic, visit your repo's landing page and select "manage topics."