What is it about?
FARC is a machine-learning (ML) based approach that predicts the bandwidth capacity for real time communications (RTC). By predicting the bandwidth accurately, FARC improves the quality of experience in RTC applications, such as video calls. FARC relies on an actor-critic structure which is a common way to train ML based solutions. The critic approach of FARC is responsible of predicting the quality while actor predicts the optimal bandwidth value.
Featured Image
Photo by Maxim Hopman on Unsplash
Why is it important?
Real time communications play a crucial role in our life and FARC can significantly improve the quality of services.
Read the Original
This page is a summary of: Offline Reinforcement Learning for Bandwidth Estimation in RTC Using a Fast Actor and Not-So-Furious Critic, April 2024, ACM (Association for Computing Machinery),
DOI: 10.1145/3625468.3652184.
You can read the full text:
Resources
Contributors
The following have contributed to this page
