mlsanityData to 14 Oct 2026

Reinforcement Learning-based Adaptive Mitigation of Uncorrected DRAM Errors in the Field

arXiv 2407.16377 ↗First posted 23 Jul 2024cs.DC cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Scaling to larger systems, with current levels of reliability, requires cost-effective methods to mitigate hardware failures. One of the main causes of hardware failure is an uncorrected error in memory, which terminates the current job and wastes all computation since the last checkpoint. This paper presents the first adaptive method for triggering uncorrected error mitigation. It uses a prediction approach that considers the likelihood of an uncorrected error and its current potential cost. The method is based on reinforcement learning, and the only user-defined parameters are the mitigation cost and whether the job can be restarted from a mitigation point. We evaluate our method using classical machine learning metrics together with a cost-benefit analysis, which compares the cost of mitigation actions with the benefits from mitigating some of the errors. On two years of production logs from the MareNostrum supercomputer, our method reduces lost compute time by 54% compared with no mitigation and is just 6% below the optimal Oracle method. All source code is open source.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 75 references that are in the map. First posted on arXiv 23 Jul 2024.

Builds on

6 of 75 references.

References · 6

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2015Prioritized Experience Replaycited by 1,099
  3. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  4. 2021Deep Reinforcement Agent for Scheduling in HPCcited by 10
  5. 2020Workload-Aware DRAM Error Prediction using Machine Learningcited by 4
  6. 2018A Workload Analysis of NSF's Innovative HPC Resources Using XDMoDcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Machine Learning-Driven Intelligent Memory System Design: From On-Chip Caches to Storage
  2. 2024Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
  3. 2026Optimal sequential decision-making for error propagation mitigation in digital twins
  4. 2025μRL: Discovering Transient Execution Vulnerabilities Using Reinforcement Learning
  5. 2026Athena: Synergizing Data Prefetching and Off-Chip Prediction via Online Reinforcement Learning
  6. 2026Mitigating the Memory Bottleneck with Machine Learning-Driven and Data-Aware Microarchitectural Techniques
  7. 2026Distributional Reinforcement Learning with Information Bottleneck for Uncertainty-Aware DRAM Equalization
  8. 2025RIFT: A Scalable Methodology for LLM Accelerator Fault Assessment using Reinforcement Learning