multi-commander/Multi-Commander

Multi & Single Agent Reinforcement Learning for Traffic Signal Control Problem

46
/ 100
Emerging

Implements both value-based (DQN, DDQN, Dueling DQN) and policy gradient (PPO, DDPG, TD3, SAC) algorithms alongside distributed methods (IMPALA, A3C, Ape-X) and multi-agent approaches (QMIX, PressLight), all integrated with CityFlow traffic simulator and Ray for distributed training. Built on CityFlow's large-scale urban traffic environment and Ray's distributed computing framework, enabling scalable single and multi-agent RL experiments with TensorFlow backend. Includes Docker containerization with pre-configured dependencies and visualization ports for rapid deployment.

130 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

130

Forks

30

Language

Python

License

Apache-2.0

Last pushed

Sep 28, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/multi-commander/Multi-Commander"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.