Skip to yearly menu bar Skip to main content


Poster

In value-based deep reinforcement learning, a pruned network is a good network

Johan Obando Ceron · Aaron Courville · Pablo Samuel Castro

Hall C 4-9 #1308
[ ] [ Paper PDF ]
Wed 24 Jul 4:30 a.m. PDT — 6 a.m. PDT

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 value-based agents to maximize parameter effectiveness. This results in networks that yield dramatic performance improvements over traditional networks, using only a small fraction of the full network parameters. Our code is publicly available, see Appendix A for details.

Chat is not available.