# Automatic Curriculum Generation for Learning Adaptation in Networking

arXiv: https://arxiv.org/abs/2202.05940 · HTML: https://mlsanity.com/paper/2202.05940/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2022.

## Built on by (most cited first, 15 of 15)

- [NetLLM: Adapting Large Language Models for Networking](https://mlsanity.com/paper/2402.02338/) (2024)
- [CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters](https://mlsanity.com/paper/2308.00852/) (2023)
- [Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices](https://mlsanity.com/paper/2212.12180/) (2022)
- [Designing Network Algorithms via Large Language Models](https://mlsanity.com/paper/2404.01617/) (2024)
- [A new hope for network model generalization](https://mlsanity.com/paper/2207.05843/) (2022)
- [OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation](https://mlsanity.com/paper/2310.02422/) (2023)
- [NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation](https://mlsanity.com/paper/2411.04138/) (2024)
- [Beyond Interpretability: Exploring the Comprehensibility of Adaptive Video Streaming through Large Language Models](https://mlsanity.com/paper/2508.16448/) (2025)
- [Towards Fair and Efficient Learning-based Congestion Control](https://mlsanity.com/paper/2403.01798/) (2024)
- [Karma: Adaptive Video Streaming via Causal Sequence Modeling](https://mlsanity.com/paper/2308.10230/) (2023)
- [SABR: A Stable Adaptive Bitrate Framework Using Behavior Cloning Pretraining and Reinforcement Learning Fine-Tuning](https://mlsanity.com/paper/2509.10486/) (2025)
- [Grounding Large Language Models as Generalizable Policies in Network Control](https://mlsanity.com/paper/2512.11839/) (2025)
- [Worst-Case Discovery and Runtime Protection for RL-Based Network Controllers](https://mlsanity.com/paper/2605.04373/) (2026)
- [Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs](https://mlsanity.com/paper/2607.23115/) (2026)
- [NetRL: Powering Network Decisions via NetGRPO-Driven Reinforcement Learning](https://mlsanity.com/paper/2610.16226/) (2026)

## Abstract (arXiv)

As deep reinforcement learning (RL) showcases its strengths in networking and systems, its pitfalls also come to the public's attention--when trained to handle a wide range of network workloads and previously unseen deployment environments, RL policies often manifest suboptimal performance and poor generalizability. To tackle these problems, we present Genet, a new training framework for learning better RL-based network adaptation algorithms. Genet is built on the concept of curriculum learning, which has proved effective against similar issues in other domains where RL is extensively employed. At a high level, curriculum learning gradually presents more difficult environments to the training, rather than choosing them randomly, so that the current RL model can make meaningful progress in training. However, applying curriculum learning in networking is challenging because it remains unknown how to measure the "difficulty" of a network environment. Instead of relying on handcrafted heuristics to determine the environment's difficulty level, our insight is to utilize traditional rule-based (non-RL) baselines: If the current RL model performs significantly worse in a network environment than the baselines, then the model's potential to improve when further trained in this environment is substantial. Therefore, Genet automatically searches for the environments where the current model falls significantly behind a traditional baseline scheme and iteratively promotes these environments as the training progresses. Through evaluating Genet on three use cases--adaptive video streaming, congestion control, and load balancing, we show that Genet produces RL policies which outperform both regularly trained RL policies and traditional baselines in each context, not only under synthetic workloads but also in real environments.