rbinzhang

Adversarial_Examples_Papers

A list of recent papers about adversarial learning

Tutorial4RL

Tutorial4RL: Tutorial for Reinforcement Learning. 强化学习入门教程.

RadarRL

RadarRL

Reinforcement Learning for Cognitive Radar (CS5073 Final Project)

DRL_RSMA_Radar_UAV

safe-control-gym

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL

MARL-Papers

Paper list of multi-agent reinforcement learning (MARL)

Adv-MARL

Adversarial attacks in consensus-based multi-agent reinforcement learning

DiffusionMTL

Code of our CVPR2024 paper - DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data

DRL-Pytorch

Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)

safe-rl-robustness

Code for "On the Robustness of Safe Reinforcement Learning under Observational Perturbations" (ICLR 2023)

OSAD

[ECCV 2020] Pytorch codes for Open-set Adversarial Defense

EMI

Boosting Transferability through Enhanced Momentum

MGAA

The code of ICCV2021 paper "Meta Gradient Adversarial Attack"

Action-Space-Adversarial-Attacks-on-DRL-Agenst

safety-gymnasium

NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark

AdverShot

Analyzing adversarial attacks on different few shot learning models.

ad3-action-distribution-divergence-detector

Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses

rl_attack

Adversarial_DRL

Adversarial attacks in deep reinforcement learning

Gym-ATC-Attack-Project

Adversarial attack for DRL in ATC

StateAdvDRL

[NeurIPS 2020, Spotlight] Code for "Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations"

swin-transformer-pytorch

Implementation of the Swin Transformer in PyTorch.

ATLA_robust_RL

Robust Reinforcement Learning with the Alternating Training of Learned Adversaries (ATLA) framework

T-SEA

[CVPR 2023] T-SEA: Transfer-based Self-Ensemble Attack on Object Detection

Metropolis-Hastings-Attacker

"Generating Fluent Adversarial Examples for Natural Languages"

nlp_adversarial_examples

Implementation code for the paper "Generating Natural Language Adversarial Examples"

Automatic-Modulation-Classification

Some Code for Master Thesis - Research on Deep Learning Based Modulation Recognition Technologies

Automatic-Target-Classification-In-SAR-Images-Using-Convolutional-Neural-Networks

SAR -> Synthetic Aperture Radar. This project is based on predicting the accuracy of the testing data set over the training data set using the MSTAR(Moving and Stationary Target Acquisition and Recognition) database and plotting the graph of the Results.csv file.

MSTAR_tensorflow

Tensorflow Project to Classify MSTAR image chips