在深度强化学习中，一个经过剪枝的网络是一个好的网络。

In deep reinforcement learning, a pruned network is a good network

February 19, 2024

作者: Johan Obando-Ceron, Aaron Courville, Pablo Samuel Castro

cs.AI

摘要

最近的研究表明，深度强化学习代理在有效利用其网络参数方面存在困难。我们利用先前对稀疏训练技术优势的见解，并展示渐进幅度剪枝使代理能够最大化参数的有效性。这导致网络产生显著的性能改进，超过传统网络，并展现出一种“缩放定律”，仅使用完整网络参数的一小部分。

English

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.