ldx123ldx1

malib

A parallel framework for population-based multi-agent reinforcement learning.

deeprl_signal_control

multi-agent deep reinforcement learning for large-scale traffic signal control.

dqn-multi-agent-rl

Deep Q-learning (DQN) for Multi-agent Reinforcement Learning (RL)

mpc-reinforcement-learning

Reinforcement Learning with Model Predictive Control

PDFormer

[AAAI2023] A PyTorch implementation of PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction.

IntelliLight

IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control

social-driving

Design multi-agent environments and simple reward functions such that social driving behavior emerges

LibSignal

RL-MPC-LaneMerging

Combining Reinforcement Learning with Model Predictive Control for On-Ramp Merging

TorchGRL

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

schlably

Official Schlably Repository by the Institute for TMDT

adaptive-tls

Adaptive real-time traffic light signal control system using Deep Multi-Agent Reinforcement Learning

CoTV

Cooperative control for traffic light signals and connected autonomous vehicles using deep reinforcement learning

Autonomous-Driving

The autonomous driving related publications of our lab.

IG-RL

Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Control

MARL_in_CAV_control_review

Multi-Agent Reinforcement Learning for Connected and Automated Vehicles Control: Recent Advancements and Future Prospects

DQN-ITSCwPD

Eco-Light

Environment friendly traffic signal control with deep reinforcement learning

decentralized_bottlenecks

Code and figures for bottlenecks paper

Double-layer-decision-making-model

An Integrated Model for Autonomous Speed and Lane Change Decision-Making Based on Deep Reinforcement Learning

Intelligent_driver_model

Simulation of car following model

GCQ_source

GCN CAV

Preference-Guided-DQN-Atari

[TNNLS] PGDQN: A generalized and efficient preference-guided epsilon-greedy policy equipped DQN for Atari and Autonomous Driving

Minimax-DQN

DQN-frameworQ

PDLight

QuadraticPlanning-based-Model-Predictive-Control-MPC-

A intelligent vehicle Model Predictive Control(MPC) implementation using QuadraticPlanning with-cruising-and-lane-change-capability

Double-DQN

Deep Q-learning is a effective reinforcement learning algorithm, but it usually over estimate the q value which influences the performance of the algorithm. Recently, some scientists came up with a improved Deep Q-learning algorithm called Double Q-learning, which uses two neural neteork to evaluate values and predict values and this new algorithm has been shown to reduce the overestimation issue effectively. In this project, I compared the performance of these two algorithms and showed that Double -learning can reduce overestimation effectively.

Deep-QLearning-Agent-for-Traffic-Signal-Control

A framework where a deep Q-Learning Reinforcement Learning agent tries to choose the correct traffic light phase at an intersection to maximize traffic efficiency.

A-DRL-solution-to-help-reduce-the-cost-in-waiting-time-of-securing-a-traffic-light-for-cyclists

Code for my paper "A DRL solution to help reduce the cost in waiting time of securing a traffic light for cyclists".