YoVDO

Gearing Up for FIFA 2022 Using RLlib-Powered Traffic Control

Offered By: Anyscale via YouTube

Tags

Multi-Agent Reinforcement Learning Courses Transportation Planning Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Learn about innovative traffic control solutions developed for the FIFA World Cup 2022 in Qatar in this 33-minute conference talk by Anyscale. Discover how researchers at Qatar Computing Research Institute (QCRI) are addressing the unprecedented challenge of managing mobility for thousands of attendees within a 20-mile radius. Explore three key components of their approach: a parallel, congestion-optimized traffic microsimulator for analyzing various scenarios; a Graph Convolutional Networks-based prediction model for traffic in-flow estimation; and a multi-agent reinforcement learning framework using RLlib for coordinated traffic light control. Gain insights into the integration of RLlib to accelerate multi-agent learning and witness a demonstration of its application in optimizing traffic flow for this major sporting event.

Syllabus

Gearing up for FIFA 2022 using RLlib-powered traffic control


Taught by

Anyscale

Related Courses

Reinforcement Learning Foundations
LinkedIn Learning
Toward Generalizable Embodied AI for Machine Autonomy
Bolei Zhou via YouTube
What Does Machine Learning Offer Game Theory - And Vice Versa
Simons Institute via YouTube
What Is the Statistical Complexity of Reinforcement Learning?
Simons Institute via YouTube
Multi-Agent Reinforcement Learning - Part II
Simons Institute via YouTube