tau="0.5" has to be removed from vType to prevent extensive vehicle collisions in simulation), it becomes difficult to reproduce paper results, which are based on SUMO 0.32.0.
#Train traffic control screenshots code
t=1500sĭue to SUMO version change and a few corresponding code modifications (e.g. large_grid/data/view.xml can be applied to visualize queue length and intersectin delay in edge color and thickness. It is recommended to have only one agent and one evaluation seed for the demo run. Python3 main.py -base-dir evaluate -agents -evaluation-seeds -demo Before training, please call build_file.py under /data/ to generate SUMO network files for small_grid and large_grid environments. Usagesįirst define all hyperparameters in a config file under, and create the base directory of experiements. Please go to branch sumo-0.32.0 if you are using the old SUMO version. Required packages can be installed by running setup_mac.sh or setup_ubuntu.sh.Īttention: the code on master branch is for SUMO version >= 1.1.0. Härri, "Monaco SUMO Traffic (MoST) Scenario: A 3D Mobility Scenario for Cooperative ITS" SUMO 2018, SUMO User Conference, Simulating Autonomous and Intermodal Transport Systems May 14-16, 2018, Berlin, Germany. A modified Monaco traffic network with 30 signalized intersections."Large-scale traffic grid signal control with regional reinforcement learning." American Control Conference (ACC), 2016. "A hierarchical model predictive control approach for signal splits optimization in large-scale urban road networks." IEEE Transactions on Intelligent Transportation Systems 17.8 (2016): 2182-2192. A 6-intersection benchmark traffic network.For more advanced algorithms, please check deeprl_network. IQL, IA2C, IA2C with stabilization (called MA2C in this paper). Decentralized: multiple local agents that make local control independently w/ neighborhood information sharing.Centralized: a global agent that makes global control w/ global observation, reward.This repo implements start-of-the-art mutli-agent (decentralized) deep RL algorithms for large-scale traffic signal control in SUMO-simulated environments.
0 kommentar(er)
