# Deep Reinforcement Learning-Based DRAM Equalizer Parameter Optimization Using Latent Representations

arXiv: https://arxiv.org/abs/2507.02365 · HTML: https://mlsanity.com/paper/2507.02365/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 26 references that are in the map.
- First posted on arXiv 3 Jul 2025.

## Builds on (most cited first, 4 of 4)

- [GPflowOpt: A Bayesian Optimization Library using TensorFlow](https://mlsanity.com/paper/1711.03845/) (2017)
- [Model-Based End-to-End Learning for WDM Systems With Transceiver Hardware Impairments](https://mlsanity.com/paper/2111.14515/) (2021)
- [Learning Physical-Layer Communication with Quantized Feedback](https://mlsanity.com/paper/1904.09252/) (2019)
- [Iterative Decision Feedback Equalization Using Online Prediction](https://mlsanity.com/paper/1810.03900/) (2018)

## Built on by (most cited first, 1 of 1)

- [Distributional Reinforcement Learning with Information Bottleneck for Uncertainty-Aware DRAM Equalization](https://mlsanity.com/paper/2603.04768/) (2026)

## Abstract (arXiv)

Equalizer parameter optimization for signal integrity in high-speed Dynamic Random Access Memory systems is crucial but often computationally demanding or model-reliant. This paper introduces a data-driven framework employing learned latent signal representations for efficient signal integrity evaluation, coupled with a model-free Advantage Actor-Critic reinforcement learning agent for parameter optimization. The latent representation captures vital signal integrity features, offering a fast alternative to direct eye diagram analysis during optimization, while the reinforcement learning agent derives optimal equalizer settings without explicit system models. Applied to industry-standard Dynamic Random Access Memory waveforms, the method achieved significant eye-opening window area improvements: 42.7% for cascaded Continuous-Time Linear Equalizer and Decision Feedback Equalizer structures, and 36.8% for Decision Feedback Equalizer-only configurations. These results demonstrate superior performance, computational efficiency, and robust generalization across diverse Dynamic Random Access Memory units compared to existing techniques. Core contributions include an efficient latent signal integrity metric for optimization, a robust model-free reinforcement learning strategy, and validated superior performance for complex equalizer architectures.