Trusted Collaboration for MEC-Enabled VR Video Streaming: A Multi-Agent Reinforcement Learning Approach

A Survey on Virtual Reality over Wireless Networks: Fundamentals, QoE, Enabling Technologies, Research Trends and Open Issues

“…Different variations of RL have drawn much interest for designing wireless VR networks [130], [148], [151], [182], [185]- [187], [226], [245], [246]. Authors in [151] proposed an asynchronous advantage actor-critic (A3C) algorithm, which employs deep RL (DRL) for jointly optimizing the viewport rendering offloading decision and downlink transmit power of the MECs in a THz wireless VR network.…”

“…A wireless VR network with collaborative MEC among the edge servers with the consideration of channel fading was proposed in [246]. An joint optimization problem is formulated for maintaining effective buffer state in VR devices, which is then solved using a multi-agent RL (MARL) approach, namely, multi-agent deep deterministic policy gradient (MADDPG) scheme.…”