English

On the Interplay Between Sparsity and Training in Deep Reinforcement Learning

Machine Learning 2025-02-04 v2 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2501.16729,
  title  = {On the Interplay Between Sparsity and Training in Deep Reinforcement Learning},
  author = {Fatima Davelouis and John D. Martin and Michael Bowling},
  journal= {arXiv preprint arXiv:2501.16729},
  year   = {2025}
}
R2 v1 2026-06-28T21:21:26.796Z