eBandit: Kernel-Driven Reinforcement Learning for Adaptive Video Streaming

arXiv:2604.08791v1 Announce Type: cross Abstract: 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.

Exploring Natural Language-Based Strategies for Efficient Number Learning in Children through Reinforcement Learning
AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction
MSG Score: Automated Video Verification for Reliable Multi-Scene Generation
Bridging Natural Language and Microgrid Dynamics: A Context-Aware Simulator and Dataset

Source: arXiv cs.AI | 2026-04-13

Related