eBandit在内核中用强化学习动态选择视频码率，提升播放质量。
eBandit: Kernel-Driven Reinforcement Learning for Adaptive Video Streaming
- 在Linux内核用eBPF运行多臂老虎机算法，实时评估三种码率策略。
- 真实场景下每块视频平均体验得分1.241，比最优静态策略高7.2%。
- 适合网络条件复杂、需快速响应的移动视频应用开发者。
用户空间的自适应码率（ABR）算法无法感知对性能至关重要的传输层信号，如最小往返时间（RTT）和瞬时传输速率，且仅在丢包已影响播放缓冲后才做出响应。本文提出eBandit框架，将网络监控与ABR算法选择移至Linux内核，利用eBPF实现。一个轻量级epsilon-greedy多臂老虎机（MAB）在sockops程序中运行，根据实时TCP指标计算奖励，评估三种ABR启发式策略。在对抗性合成数据上，eBandit累计用户体验得分（QoE）达416.3 ± 4.9，优于最优静态策略7.2%。在42个真实世界会话中，每块视频平均QoE为1.241，是所有策略中的最高值，证明了内核级强化学习在异构移动环境下的有效迁移。
原文摘要 · Abstract (English)
User-space Adaptive Bitrate (ABR) algorithms cannot see the transport layer signals that matter most, such as minimum RTT and instantaneous delivery rate, and they respond to network changes only after damage has already propagated to the playout buffer. We present eBandit, a framework that relocates both network monitoring and ABR algorithm selection into the Linux kernel using eBPF. A lightweight epsilon-greedy Multi-Armed Bandit (MAB) runs inside a sockops program, evaluating three ABR heuristics against a reward derived from live TCP metrics. On an adversarial synthetic trace eBandit achieves $416.3 \pm 4.9$ cumulative QoE, outperforming the best static heuristic by $7.2\%$. On 42 real-world sessions eBandit achieves a mean QoE per chunk of $1.241$, the highest across all policies, demonstrating that kernel-resident bandit learning transfers to heterogeneous mobile conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。