Cargando…
Deep reinforcement learning with significant multiplications inference
We propose a sparse computation method for optimizing the inference of neural networks in reinforcement learning (RL) tasks. Motivated by the processing abilities of the brain, this method combines simple neural network pruning with a delta-network algorithm to account for the input data correlation...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Nature Publishing Group UK
2023
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10682459/ https://www.ncbi.nlm.nih.gov/pubmed/38012259 http://dx.doi.org/10.1038/s41598-023-47245-y |