返回文献探索AI 摘要
Paper · arXiv 2402.12479
In deep reinforcement learning, a pruned network is a good network
Johan Obando-Ceron, Aaron Courville, Pablo Samuel Castro
19 upvotesFebruary 19, 2024arXiv 预印本
Gradual magnitude pruning in deep reinforcement learning enhances parameter effectiveness, improving performance and achieving scaling law efficiency.
sparse trainingmagnitude pruningparameter effectivenessscaling law
Abstract
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 agents to maximize parameter effectiveness. This results in networks that yield dramatic performance improvements over traditional networks and exhibit a type of "scaling law", using only a small fraction of the full network parameters.