Metraipolis › archive › dc_10b7142faef7
Deep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation — arXiv:2610.21008
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21008
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T08:59:38.176Z
- SHA-256 of the archived text
8806bca81e735015bf6dfa4a17bc81f6f6fad51633ce7c6f97fe19859ac26b2f- Stable URL of this page
https://metraipolis.com/documento/dc_10b7142faef7
How to cite
Deep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation — arXiv:2610.21008 — arXiv (en), https://arxiv.org/abs/2610.21008 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10b7142faef7 (Metraipolis archive dc_10b7142faef7, sha256 8806bca81e735015bf6dfa4a17bc81f6f6fad51633ce7c6f97fe19859ac26b2f)
BibTeX
@misc{dc10b7142faef7,
title = {Deep Reinforcement Learning for HPC Job Scheduling: A Statistical Evaluation — arXiv:2610.21008},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21008},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10b7142faef7; sha256 8806bca81e735015bf6dfa4a17bc81f6f6fad51633ce7c6f97fe19859ac26b2f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21008. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep Reinforcement Learning (DRL) offers learned job selection for High-Performance Computing (HPC), but performance against heuristics alone does not establish value beyond action masking. Six DRL treatments are compared: Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Q-Network (DQN), each with and without masking. Three heuristics and a seed-paired masked uniform random control provide baselines across ten seeds on two real Slurm (Simple Linux Utility for Resource Management) workload traces, one homogeneous and one heterogeneous, under a common non-parametric framework. All masked treatments complete evaluation, whereas unmasked treatments are truncated. On the homogeneous trace, no masked DRL treatment significantly improves average waiting time or average and maximum bounded slowdown over the control. On the heterogeneous trace, MaskablePPO improves all three metrics relative to the control. Its average waiting time is equivalent to that of the three heuristics within a 10% margin, and its maximum bounded slowdown is 22% lower than that of Last-Come, First-Served (LCFS). MaskablePPO has the leading average waiting-time rank among complete treatments on both traces, but Nemenyi comparisons detect no significant difference from MaskableA2C. Among masked variants, MaskablePPO has the lowest recorded mean training time, while MaskableDQN has the lowest mean decision latency. These findings distinguish completion from baseline-specific scheduling gains and support including a masked random control when assessing the value of learned selection. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.21008 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:17.685Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).