Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.17309 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915871354519552 |
|---|---|
| author | Sai, Panuganti Chirag Sarat, Gandholi Sarma, R. Raghunatha Tavva, Venkata Kalyan M, Naveen |
| author_facet | Sai, Panuganti Chirag Sarat, Gandholi Sarma, R. Raghunatha Tavva, Venkata Kalyan M, Naveen |
| contents | Reducing latency and energy consumption is critical to improving the efficiency of memory systems in modern computing. This work introduces ReLMXEL (Reinforcement Learning for Memory Controller with Explainable Energy and Latency Optimization), a explainable multi-agent online reinforcement learning framework that dynamically optimizes memory controller parameters using reward decomposition. ReLMXEL operates within the memory controller, leveraging detailed memory behavior metrics to guide decision-making. Experimental evaluations across diverse workloads demonstrate consistent performance gains over baseline configurations, with refinements driven by workload-specific memory access behaviour. By incorporating explainability into the learning process, ReLMXEL not only enhances performance but also increases the transparency of control decisions, paving the way for more accountable and adaptive memory system designs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17309 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization Sai, Panuganti Chirag Sarat, Gandholi Sarma, R. Raghunatha Tavva, Venkata Kalyan M, Naveen Hardware Architecture Artificial Intelligence Machine Learning Multiagent Systems Systems and Control Reducing latency and energy consumption is critical to improving the efficiency of memory systems in modern computing. This work introduces ReLMXEL (Reinforcement Learning for Memory Controller with Explainable Energy and Latency Optimization), a explainable multi-agent online reinforcement learning framework that dynamically optimizes memory controller parameters using reward decomposition. ReLMXEL operates within the memory controller, leveraging detailed memory behavior metrics to guide decision-making. Experimental evaluations across diverse workloads demonstrate consistent performance gains over baseline configurations, with refinements driven by workload-specific memory access behaviour. By incorporating explainability into the learning process, ReLMXEL not only enhances performance but also increases the transparency of control decisions, paving the way for more accountable and adaptive memory system designs. |
| title | ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization |
| topic | Hardware Architecture Artificial Intelligence Machine Learning Multiagent Systems Systems and Control |
| url | https://arxiv.org/abs/2603.17309 |