Reinforcement Learning for Datacenter Congestion Control. (arXiv:2102.09337v2 [cs.LG] UPDATED)

We approach the task of network congestion control in datacenters using
Reinforcement Learning (RL). Successful congestion control algorithms can
dramatically improve latency and overall network throughput. Until today, no
such learning-based algorithms have shown practical potential in this domain.
Evidently, the most popular recent deployments rely on rule-based heuristics
that are tested on a predetermined set of benchmarks. Consequently, these
heuristics do not generalize well to newly-seen scenarios. Contrarily, we
devise an RL-based algorithm with the aim of generalizing to …

arxiv congestion datacenter learning lg reinforcement reinforcement learning