?機(jī)器學(xué)習(xí)搞得火熱朝天塌西,搞網(wǎng)絡(luò)的也向跟著熱一把。但是能網(wǎng)絡(luò)能和機(jī)器學(xué)習(xí)扯上關(guān)系的筝尾,似乎也就是增強(qiáng)學(xué)習(xí)捡需。這里就對增強(qiáng)學(xué)習(xí)與網(wǎng)絡(luò)相關(guān)的論文做個整理。論文中結(jié)論無一例外忿等,都是很好栖忠。
congestion control
- QTCP: Adaptive congestion control with reinforcement learning
- TCP ex Machina: Computer-Generated Congestion Control
- An Experimental Study of the Learnability of Congestion Control
- Internet Congestion Control via Deep Reinforcement Learning
- TCP-Drinc: Smart Congestion Control Based on Deep Reinforcement Learning
- Dynamic TCP Initial Windows and Congestion Control Schemes Through Reinforcement Learning
- PCC Vivace: Online-Learning Congestion Control
- Delay-Constrained Rate Control for Real-Time Video Streaming with Bounded Neural Network
- Multi-Armed Bandit Congestion Control in Multi-Hop Infrastructure Wireless Mesh Networks
- Improving TCP Congestion Control with Machine Intelligence
- Multi-Armed Bandit in Action: Optimizing Performance in Dynamic Hybrid Networks
- Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control
code https://github.com/dcgym/iroko - Dynamic TCP Initial Windows and Congestion Control Schemes Through Reinforcement Learning
mptcp
- A Reinforcement Learning Approach for Multipath TCP Data Scheduling
- ReLeS: A Neural Adaptive Multipath Scheduler based on Deep Reinforcement Learning
- SmartCC: A Reinforcement Learning Approach for Multipath TCP Congestion Control in Heterogeneous Networks
- Experience-driven Congestion Control: When Multi-Path TCP Meets Deep Reinforcement Learning
- Peekaboo: Learning-based Multipath Scheduling for Dynamic Heterogeneous Environments
dash
- D-DASH: A deep Q-learning framework for DASH video streaming
- Online learning adaptation strategy for DASH clients
- Continual learning improves Internet video streaming
- Neural Adaptive Video Streaming with Pensieve
- Tiyuntsong: A Self-Play Reinforcement Learning Approach for ABR Video Streaming
- PiTree: Practical Implementation of ABR Algorithms Using Decision Trees
- HotDASH: Hotspot Aware Adaptive Video Streaming using Deep Reinforcement Learning (code:https://github.com/SatadalSengupta/hotdash)
multimedia streaming
- QARC: Video Quality Aware Rate Control for Real-Time Video Streaming based on Deep Reinforcement Learning
- LEAP: Learning-Based Smart Edge with Caching and Prefetching for Adaptive Video Streaming
Routing
- Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN
code: https://github.com/knowledgedefinednetworking/a-deep-rl-approach-for-sdn-routing-optimization