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

Johan Samir Obando Ceron, Aaron Courville, Pablo Samuel Castro

In deep reinforcement learning, a pruned network is a good network: 19 upvotes on Hugging Face Daily Papers, #6 of 12 papers on 2024-02-22. Day-by-day upvote history.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.