wulihan20212021

ChuanhuChatGPT

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

StateAdvDRL

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

rebel

An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.

tarok

:spades: Slovenian Tarok card game environment for the OpenSpiel framework.

Reinforcement_Learning_In_Two_Player_Simultaneous_Action_Games

Nash-DQN

Deep Reinforcement Learning for Nash Equilibria

Quickest-Detection-FDI-Remote-Estimation

Code for our paper titled "Quickest detection of false data injection in remote state estimation" published at IEEE ISIT 2021.

Soft-Actor-Critic-Reinforcement-Learning-Mobile-Robot-Navigation

This example uses Soft Actor Critic(SAC) based reinforcement learning to develop the mobile robot navigation. For a brief summary of the SAC algorithm, see Soft Actor Critic(SAC) Agents. This example scenario trains a mobile robot to navigate from location A to location B to avoid obstacles given range sensor readings that detect obstacles in the map. The objective of the reinforcement learning algorithm is to learn what controls (linear and angular velocity) for navigation from an initial to goal position and during the travel also can avoid colliding into obstacles. This example uses an occupancy map of a known environment to generate range sensor readings, detect obstacles, and check collisions the robot may make. The range sensor readings are the observations for the SAC agent, and the linear and angular velocity controls are the action.

Reinforcement_learning-PID-auto-tuning

Auto tuning of PID parameters of a quad-rotor using Q-learning

rl-agent-based-traffic-control

Develop agent-based traffic management system by model-free reinforcement learning

swarm_evolve

Model-Based Stochastic Search for Large Scale Optimization of Multi-Agent UAV Swarms

DRLCyberAssessment_DQNCode

Adv-MARL

Adversarial attacks in consensus-based multi-agent reinforcement learning

NetworkSecRLwithPareto

Network Security Attack and Defence Strategy selection using Reinforcement Learning and Pareto efficiency

SDN_DDoS_Simulation

An attempt to detect and prevent DDoS attacks using reinforcement learning. The simulation was done using Mininet.

differentially-private-q-learning

tsg19

MARL-Papers

Paper list of multi-agent reinforcement learning (MARL)