Official implementation of HARL algorithms based on PyTorch.

Open code of my published paper: Eco-Driving Framework for Hybrid Electric Vehicles in Multi-Lane Scenarios by Using Deep Reinforcement Learning Methods

A research-driven simulation system that optimizes urban bus scheduling using multi-agent reinforcement learning (MARL). The project integrates GTFS transit data, SUMO traffic simulation, and RLlib…

applying multi-agent reinforcement learning for highway-merging autonomous vehicles

Source code for paper "A Differentiated Reward Method for Reinforcement Learning Based Multi-Vehicle Cooperative Decision-Making Algorithms"

MARL for Autonomous Vehicles

Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space

Concise pytorch implements of MARL algorithms, including MAPPO, MADDPG, MATD3, QMIX and VDN.

MAPPO-PIS：MAPPO with Prior Intent Sharing

DGN Code

The source code for our paper: Graph Reinforcement Learning Application to Co-operative Decision-Making in Mixed Autonomy Traffic: Framework, Survey, and Challenges. This code is developed based on…

TorchGRL is the source code for our paper Graph Convolution-Based Deep Reinforcement Learning for Multi-Agent Decision-Making in Mixed Traffic Environments.

Code for a multiple cooperative-mpc for multiple vehicles (esp. ambulance)

The pytorch implementation of DGN on grid world and Starcraft

This algorithm can quickly plan the optimal trajectory for the vehicle in complex scenarios.

Data-driven Trajectory Planning Strategy for Connected Vehicles at Signalized Intersection

Hybrid A Star Trajectory Planning in multi-vehicle cooperative planning in narrow free space.

A generalized framework for prototyping full-stack cooperative driving automation applications under CARLA+SUMO.

Efficient Multi-Vehicle Trajectory Planning via Centralized Searching Decentralized Optimization

Official code implementation for "Efficient and Distributed Multi-Agent Interactive Trajectory Optimization via ADMM and Dynamic Potential Games"

Project to improve the efficiency of traffic signal control and reduce traffic delay at intersections by using various optimization algorithms.

Code for "Traffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies"

Algorithm for distributed traffic signal control

SUMO Simulation source code of the study - A Study of Applying Eco-Driving Speed Advisory on Transit Signal Priority

Code for "Evaluation of transit signal priority at signalized intersections under connected vehicle environment"

Open code of my published paper: Ecological Driving Framework of Hybrid Electric Vehicle Based on Heterogeneous Multi-Agent Deep Reinforcement Learning