Client-side video players employ adaptive bitrate (ABR) algorithms to optimize user quality of experience (QoE). We evaluate recently proposed RL-based ABR methods in Facebook's web-based video streaming platform. Real-world ABR contains several challenges that requires customized designs beyond off-the-shelf RL algorithms -- we implement a scalable neural network architecture that supports videos with arbitrary bitrate encodings; we design a training method to cope with the variance resulting from the stochasticity in network conditions; and we leverage constrained Bayesian optimization for reward shaping in order to optimize the conflicting QoE objectives. In a week-long worldwide deployment with more than 30 million video streaming sessions, our RL approach outperforms the existing human-engineered ABR algorithms.
@article{arxiv.2008.12858,
title = {Real-world Video Adaptation with Reinforcement Learning},
author = {Hongzi Mao and Shannon Chen and Drew Dimmery and Shaun Singh and Drew Blaisdell and Yuandong Tian and Mohammad Alizadeh and Eytan Bakshy},
journal= {arXiv preprint arXiv:2008.12858},
year = {2020}
}
Comments
Reinforcement Learning for Real Life (RL4RealLife) Workshop in the 36th International Conference on Machine Learning, Long Beach, California, USA, 2019