ChatPaper.aiChatPaper

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

February 19, 2024
Authors: Johan Obando-Ceron, Aaron Courville, Pablo Samuel Castro
cs.AI

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.

PDF191December 15, 2024