在深度強化學習中，一個經過修剪的網絡是一個好的網絡。

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

最近的研究顯示，深度強化學習代理程序在有效利用其網絡參數方面存在困難。我們利用先前對於稀疏訓練技術優勢的洞察，證明逐漸減少大小的修剪使代理程序能夠最大化參數的效能。這導致網絡產生比傳統網絡更顯著的性能改進，並展現出一種“擴展定律”，僅使用完整網絡參數的一小部分。

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.