When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control 事件

When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control arXiv:2605.26418v1 Announce Type: cross Abstract: A properly calibrated rule-based autoscaler can beat every one of six mainstream deep reinforcement learning (DRL) algorithms on cost across every workload we test - so when, if ever, does DRL actually help? We study this in RLScale-Bench, a reproducible benchmark and evaluation protocol for DRL on adaptive resource control, where an agent allocates compu