|
ИСТИНА |
Войти в систему Регистрация |
ИПМех РАН |
||
Neural network compression for reinforcement learning tasksстатья
Статья опубликована в высокорейтинговом журнале
Информация о цитировании статьи получена из
Scopus
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 23 апреля 2025 г.
- Авторы: Ivanov Dmitry A., Larionov Denis A., Maslennikov Oleg V., Voevodin Vladimir V.
- Журнал: Scientific reports
- Том: 15
- Номер: 1
- Год издания: 2025
- Издательство: Nature Publishing Group
- Местоположение издательства: United Kingdom
- Первая страница: 9718
- DOI: 10.1038/s41598-025-93955-w
- Аннотация: In real applications of Reinforcement Learning (RL), such as robotics, low latency, energy-efficient and high-throughput inference is very desired. The use of sparsity and pruning for optimizing Neural Network inference, and particularly to improve energy efficiency, latency and throughput, is a standard technique. In this work, we conduct a systematic investigation of the application of these optimization techniques with popular RL algorithms, specifically Deep Q-Network and Soft Actor Critic, in different RL environments, including MuJoCo and Atari, which yields up to a 400-fold reduction in the size of neural networks. This work presents a systematic study on the applicability limits of using pruning and quantization to optimize neural networks in RL tasks, with a perspective of deployment in hardware to reduce power consumption and latency, while increasing throughput.
- Добавил в систему: Иванов Дмитрий Александрович