In deep reinforcement learning, a pruned network is a good network
CoRR(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要