On the Interplay Between Sparsity and Training in Deep Reinforcement Learning

Bibliographic Details
Title: On the Interplay Between Sparsity and Training in Deep Reinforcement Learning
Authors: Davelouis, Fatima, Martin, John D., Bowling, Michael
Publication Year: 2025
Collection: Computer Science
Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence
More Details: We study the benefits of different sparse architectures for deep reinforcement learning. In particular, we focus on image-based domains where spatially-biased and fully-connected architectures are common. Using these and several other architectures of equal capacity, we show that sparse structure has a significant effect on learning performance. We also observe that choosing the best sparse architecture for a given domain depends on whether the hidden layer weights are fixed or learned.
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2501.16729
Accession Number: edsarx.2501.16729
Database: arXiv
More Details
Description not available.