Heterogeneous 360 Degree Videos in Metaverse: Differentiated Reinforcement Learning Approaches
This work addresses the challenge of managing diverse video types in the Metaverse, which is incremental as it builds on existing reinforcement learning methods for a specific domain.
The paper tackles the problem of optimizing quality of service for heterogeneous 360-degree videos in the Metaverse by proposing a frame-slotted structure and differentiated deep reinforcement learning algorithms, achieving improved performance in frame rates and cybersickness reduction as demonstrated through experiments.
Advanced video technologies are driving the development of the futuristic Metaverse, which aims to connect users from anywhere and anytime. As such, the use cases for users will be much more diverse, leading to a mix of 360-degree videos with two types: non-VR and VR 360-degree videos. This paper presents a novel Quality of Service model for heterogeneous 360-degree videos with different requirements for frame rates and cybersickness. We propose a frame-slotted structure and conduct frame-wise optimization using self-designed differentiated deep reinforcement learning algorithms. Specifically, we design two structures, Separate Input Differentiated Output (SIDO) and Merged Input Differentiated Output (MIDO), for this heterogeneous scenario. We also conduct comprehensive experiments to demonstrate their effectiveness.