In Value-Based Deep Reinforcement Learning, a Pruned Network Is a Good Network
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.
Cite
Text
Obando Ceron et al. "In Value-Based Deep Reinforcement Learning, a Pruned Network Is a Good Network." International Conference on Machine Learning, 2024.Markdown
[Obando Ceron et al. "In Value-Based Deep Reinforcement Learning, a Pruned Network Is a Good Network." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/obandoceron2024icml-valuebased/)BibTeX
@inproceedings{obandoceron2024icml-valuebased,
title = {{In Value-Based Deep Reinforcement Learning, a Pruned Network Is a Good Network}},
author = {Obando Ceron, Johan Samir and Courville, Aaron and Castro, Pablo Samuel},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {38495-38519},
volume = {235},
url = {https://mlanthology.org/icml/2024/obandoceron2024icml-valuebased/}
}