HTTP Adaptive Streaming Framework with Online Reinforcement Learning

Dynamic adaptive streaming over HTTP (DASH) is an effective method for improving video streaming's quality of experience (QoE). However, the majority of existing schemes rely on heuristic algorithms, and the learning-based schemes that have recently emerged also have a problem in that their performance deteriorates in a specific environment. In this study, we propose an adaptive streaming scheme that applies online reinforcement learning. When QoE degradation is confirmed, the proposed scheme adapts to changes in the client's environment by upgrading the ABR model while performing video streaming. In order to adapt the adaptive bitrate (ABR) model to a changing network environment while performing video streaming, the neural network model is trained with a state-of-the-art reinforcement learning algorithm. The proposed scheme's performance was evaluated using simulation-based experiments under various network conditions. The experimental results confirmed that the proposed scheme performed better than the existing schemes.

Automated summary

In this study, an adaptive streaming scheme using online reinforcement learning is proposed to improve the quality of video streaming. The scheme adapts to changes in client environment by upgrading the ABR model and utilizes state-of-the-art reinforcement learning algorithm to train the neural network model during video streaming.