Saved in:
Bibliographic Details
Main Authors: Lu, Heng, Alemi, Mehdi, Rawassizadeh, Reza
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.04803
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910515776716800
author Lu, Heng
Alemi, Mehdi
Rawassizadeh, Reza
author_facet Lu, Heng
Alemi, Mehdi
Rawassizadeh, Reza
contents Deep reinforcement learning (DRL) has achieved remarkable success across various domains, such as video games, robotics, and, recently, large language models. However, the computational costs and memory requirements of DRL models often limit their deployment in resource-constrained environments. The challenge underscores the urgent need to explore neural network compression methods to make RDL models more practical and broadly applicable. Our study investigates the impact of two prominent compression methods, quantization and pruning on DRL models. We examine how these techniques influence four performance factors: average return, memory, inference time, and battery utilization across various DRL algorithms and environments. Despite the decrease in model size, we identify that these compression techniques generally do not improve the energy efficiency of DRL models, but the model size decreases. We provide insights into the trade-offs between model compression and DRL performance, offering guidelines for deploying efficient DRL models in resource-constrained settings.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04803
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Impact of Quantization and Pruning on Deep Reinforcement Learning Models
Lu, Heng
Alemi, Mehdi
Rawassizadeh, Reza
Machine Learning
Artificial Intelligence
Deep reinforcement learning (DRL) has achieved remarkable success across various domains, such as video games, robotics, and, recently, large language models. However, the computational costs and memory requirements of DRL models often limit their deployment in resource-constrained environments. The challenge underscores the urgent need to explore neural network compression methods to make RDL models more practical and broadly applicable. Our study investigates the impact of two prominent compression methods, quantization and pruning on DRL models. We examine how these techniques influence four performance factors: average return, memory, inference time, and battery utilization across various DRL algorithms and environments. Despite the decrease in model size, we identify that these compression techniques generally do not improve the energy efficiency of DRL models, but the model size decreases. We provide insights into the trade-offs between model compression and DRL performance, offering guidelines for deploying efficient DRL models in resource-constrained settings.
title The Impact of Quantization and Pruning on Deep Reinforcement Learning Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2407.04803