Research map / Reinforcement learning / Visual and representation RL
A Deep Reinforcement Learning Perspective on Internet Congestion Control
Nathan Jay, Noga Rotman, Brighten Godfrey, Michael Schapira, Aviv Tamar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Train congestion control policy with deep RL (PPO) on simulated links, with linear reward (throughput, latency, loss) | Aurora · Mininet/Pantheon robustness tests | link utilization and self-inflicted latency | Improved |
| Use discount factor gamma=0.99 instead of 0.5 or 0.0 (ablation) | Aurora training · Training reward | learning speed | Improved |
| Increase history length from 1 to 2 MIs (ablation) | Aurora · Training reward | training reward | Improved |
| Aurora trained on dynamic-like links versus TCP CUBIC on dynamic links | Aurora · Dynamic links (16-32 Mbps random) | throughput nearly matching BBR with significantly better latency | Improved |
| Replace linear-model / bandit formulations with a small 2-hidden-layer neural network (32→16, tanh) (ablation) | Aurora · Training reward | training reward | Improved |
| Aurora with 1% random loss vs TCP CUBIC | Aurora · Single flow 30 Mbps with 1% random loss | throughput | Improved |
| Aurora on fairness with TCP or other protocols | Aurora · Fairness (not evaluated) | fairness | No clear effect |
Closest papers by meaning
- URB - Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles (NeurIPS 2025 · similarity 0.85)
- NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation (NeurIPS 2024 · similarity 0.84)
- Deep Reinforcement Learning for Communication Networks (AAAI 2024 · similarity 0.84)
- Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning (NeurIPS 2025 · similarity 0.84)
- SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores (ICLR 2024 · similarity 0.84)
- Imitation Learning Backoff: Reinforcement Learning-based Channel Access for Guaranteeing Fairness (Student Abstract) (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
