ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization

TL;DR

ReLMXEL is an explainable reinforcement learning framework that dynamically optimizes memory controller parameters to reduce latency and energy consumption, improving efficiency and transparency in memory systems.

Contribution

This work introduces ReLMXEL, a novel multi-agent RL-based memory controller with explainability, enabling adaptive optimization and increased transparency in decision-making.

Findings

Achieves performance improvements over baseline configurations.

Demonstrates workload-specific optimization capabilities.

Enhances transparency and accountability in memory control decisions.

Abstract

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.