Reinforcement Learning Based Adaptive Bitrate Algorithm for Transmitting Panoramic Videos

Intelligent Video Streaming at Network Edge: An Attention-Based Multiagent Reinforcement Learning Solution

“…However, both of the above two methods are highly dependent on the assumption of prediction accuracy, which can be hardly competent in the sophisticated environment and heterogeneous user demand. In [19], the authors proposed a method based on a reinforcement learning algorithm to select the bitrates of the region of interest adaptively for panoramic videos. In [20], in order to optimize the QoE, the authors proposed a novel ABR algorithm considering the user preference based on short trajectory segments.…”

“…Reinforcement Learning [17] Detecting bandwidth changes using smoothed HTTP throughput based on the segment fetch time [18] Investigating rate adaptation for the serial segment fetching method and the parallel segment fetching method in a content distribution network [14] Developing a set of techniques to trade off stability, fairness, and efficiency in the video adaptive framework [13] Designing a video bitrate adaptive algorithm at the application layer [15] Proposing the video buffer to ease the need for capacity [1] Modeling the edge user allocation problem as a bin packing problem [2] Enabling flexible levels of QoE for app users [19] Selecting the bitrates of the region of interest adaptively for panoramic videos [10] Considering the edge user allocation problem as an online decision-making and evolvable process [20] Considering user preference based on short trajectory segments [16] Using Lyapunov optimization to minimize rebuffering and maximize video quality [9] Investigating the EUA problem in a NOMA-based MEC system [11] Solving the dynamic EUA problem with mutual interference between users [5] Predicting resource utilization of user requests for better user allocation [12] Maximizing the data rate of the total network and prioritizing the quality of service for key users…”