Neural Network Compression for Reinforcement Learning Tasks

Dmitry A. Ivanov, Denis A. Larionov, Oleg V. Maslennikov, Vladimir V. Voevodin
5/13/2024
cs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

In real applications of Reinforcement Learning (RL), such as robotics, low latency and energy efficient inference is very desired. The use of sparsity and pruning for optimizing Neural Network inference, and particularly to improve energy and latency efficiency, is a standard technique. In this work, we perform a systematic investigation of applying these optimization techniques for different RL algorithms in different RL environments, yielding up to a 400-fold reduction in the size of neural networks.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

The Impact of Quantization and Pruning on Deep Reinforcement Learning Models

88% match2024

Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning

85% match2024

Online Training and Pruning of Deep Reinforcement Learning Networks

85% match2025

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

85% match1 repo412025

Fast as CHITA: Neural Network Pruning with Combinatorial Optimization

84% match1 repo142026

RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration

84% match1 repo292024

Cite this paper

@article{ivanov2024neural,
  title  = {Neural Network Compression for Reinforcement Learning Tasks},
  author = {Dmitry A. Ivanov and Denis A. Larionov and Oleg V. Maslennikov and Vladimir V. Voevodin},
  year   = {2024},
  eprint = {2405.07748},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.07748v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.07748.svg)](https://codeofpaper.com/paper/2405.07748)

Discussion