shaoruchen Goto Github PK

admm-nn-reachability

alpha-beta-crown

alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP'21)

auto_lirpa

[NeurIPS 2020]auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks

automatedreach

cartpole

OpenAI's cartpole env solver.

cartpolesimulation

This repository contains CartPole simulator with its GUI, implemented controller (LQR) and generator of random desired position trace. It also contains files to train and test RNN predicting future states of a CartPole.

composite_cbf

Learn a neural network control barrier function subject to safety constraints composited by logical operations.

convex_adversarial

A method for training neural networks that are provably robust to adversarial attacks.

decomposition-plnn-bounds

Dual iterative algorithms for Neural Network output bounds computations

deeplearning-models

A collection of various deep learning architectures, models, and tips

deepsplit

Solving the linear programming-based neural network verification problem through Alternating Direction Method of Multipliers (ADMM).

ellm

gym

A toolkit for developing and comparing reinforcement learning algorithms.

hybrid-ocp-yalmip

Solve hybrid OCPs with occupation measures on Yalmip

keras-rl

Deep Reinforcement Learning for Keras.

keras-rl2

Reinforcement learning with tensorflow 2 keras

learning-cbfs

Code needed to reproduce the examples found in "Learning Control Barrier Functions from Expert Demonstrations," by A. Robey, H. Hu, L. Lindemann, H. Zhang, D. V. Dimarogonas, S. Tu, and N. Matni, https://arxiv.org/abs/2004.03315

learning-nn-roa

A cutting-plane method to synthesize Lyapunov functions for neural network uncertain systems.

lumped-uncertainty-sls-mpc

Robust model predictive control of uncertain linear dynamical systems subject to polytopic model uncertainty and additive disturbances.

neural-barrier-function

Learn a NN vector barrier function with a convex optimization-based fine-tuning step.

neural-network-lyapunov

Synthesizing neural-network Lyapunov functions (and controllers) as stability certificate.

nn-system-psf

Solving a constrained robust optimal control problem with uncertain neural network dynanmics through convex optimization.

nn-system-reachability

Finite-step reachable set over-approximation of NN dynamical systems using the one-shot and recursive methods.

polytopic-slsmpc

Implement SLS MPC for linear systems subject to polytopic model uncertainty and additive disturbances.

pwa-control

Control of piecewise affine systems

reinforcement-learning-an-introduction

Python Implementation of Reinforcement Learning: An Introduction

robust-optimal-control

Robust optimal control of nonlinear systems

sa_dqn

[NeurIPS 2020, Spotlight] State-Adversarial DQN (SA-DQN) for robust deep reinforcement learning

shaoruchen.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

spotless

A fork of the Systems Polynomial Optimization Toolbox.