In value-based deep reinforcement learning, a pruned network is a good network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Obando-Ceron, Johan, Courville, Aaron, Castro, Pablo Samuel
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909230892580864
author Obando-Ceron, Johan
Courville, Aaron
Castro, Pablo Samuel
author_facet Obando-Ceron, Johan
Courville, Aaron
Castro, Pablo Samuel
contents Recent work has shown that deep reinforcement learning agents have difficulty in effectively using their network parameters. We leverage prior insights into the advantages of sparse training techniques and demonstrate that gradual magnitude pruning enables value-based agents to maximize parameter effectiveness. This results in networks that yield dramatic performance improvements over traditional networks, using only a small fraction of the full network parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12479
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle In value-based deep reinforcement learning, a pruned network is a good network
Obando-Ceron, Johan
Courville, Aaron
Castro, Pablo Samuel
Machine Learning
Artificial Intelligence
Recent work has shown that deep reinforcement learning agents have difficulty in effectively using their network parameters. We leverage prior insights into the advantages of sparse training techniques and demonstrate that gradual magnitude pruning enables value-based agents to maximize parameter effectiveness. This results in networks that yield dramatic performance improvements over traditional networks, using only a small fraction of the full network parameters.
title In value-based deep reinforcement learning, a pruned network is a good network
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2402.12479