# EdgeRL: Reinforcement Learning-driven Deep Learning Model Inference Optimization at Edge

arXiv: https://arxiv.org/abs/2410.12221 · HTML: https://mlsanity.com/paper/2410.12221/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 7 of 7)

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing](https://mlsanity.com/paper/2201.02693/) (2022)
- [Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems](https://mlsanity.com/paper/2304.10892/) (2023)
- [Reinforcement Learning-driven Data-intensive Workflow Scheduling for Volunteer Edge-Cloud](https://mlsanity.com/paper/2407.01428/) (2024)
- [IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency](https://mlsanity.com/paper/2308.12871/) (2023)
- [A Tale of Two Scales: Reconciling Horizontal and Vertical Scaling for Inference Serving Systems](https://mlsanity.com/paper/2407.14843/) (2024)

## Built on by (most cited first, 2 of 2)

- [Reinforcement Learning-Driven Edge Management for Reliable Multi-view 3D Reconstruction](https://mlsanity.com/paper/2510.08839/) (2025)
- [EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression](https://mlsanity.com/paper/2609.11058/) (2026)

## Abstract (arXiv)

Balancing mutually diverging performance metrics, such as, processing latency, outcome accuracy, and end device energy consumption is a challenging undertaking for deep learning model inference in ad-hoc edge environments. In this paper, we propose EdgeRL framework that seeks to strike such balance by using an Advantage Actor-Critic (A2C) Reinforcement Learning (RL) approach that can choose optimal run-time DNN inference parameters and aligns the performance metrics based on the application requirements. Using real world deep learning model and a hardware testbed, we evaluate the benefits of EdgeRL framework in terms of end device energy savings, inference accuracy improvement, and end-to-end inference latency reduction.