# eBandit: Kernel-Driven Reinforcement Learning for Adaptive Video Streaming

arXiv: https://arxiv.org/abs/2604.08791 · HTML: https://mlsanity.com/paper/2604.08791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 2 of its 12 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 2 of 2)

- [BOLA: Near-Optimal Bitrate Adaptation for Online Videos](https://mlsanity.com/paper/1601.06748/) (2016)
- [CBA: Contextual Quality Adaptation for Adaptive Bitrate Video Streaming (Extended Version)](https://mlsanity.com/paper/1901.05712/) (2019)

## Abstract (arXiv)

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 ± 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.