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

ArXiv CS.AI2026-05-27NEWSen作者: Guilin Zhang, Chuanyi Sun, Kai Zhao, Shahryar Sarkani, John Fossaceca

查看原文 →

When Does Deep RL Beat Calibrated Baselines? A Benchmark Study on Adaptive Resource Control · 相关技术

相关技术

TTE Kubernetes 远程代码执行（RCE）reward function reinforcement learning eval divide-and-conquer partitioning Stan Soft Actor Critic PROBE PPO HIS For FFI Deep RL DQN DAPT ANN Agent ICE