A Hardware-oriented Approach for Efficient Active Inference Computation and Deployment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pižurica, Nikola, Milović, Nikola, Jovančević, Igor, Heins, Conor, de Prado, Miguel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918126721957888
author Pižurica, Nikola
Milović, Nikola
Jovančević, Igor
Heins, Conor
de Prado, Miguel
author_facet Pižurica, Nikola
Milović, Nikola
Jovančević, Igor
Heins, Conor
de Prado, Miguel
contents Active Inference (AIF) offers a robust framework for decision-making, yet its computational and memory demands pose challenges for deployment, especially in resource-constrained environments. This work presents a methodology that facilitates AIF's deployment by integrating pymdp's flexibility and efficiency with a unified, sparse, computational graph tailored for hardware-efficient execution. Our approach reduces latency by over 2x and memory by up to 35%, advancing the deployment of efficient AIF agents for real-time and embedded applications.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13177
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Hardware-oriented Approach for Efficient Active Inference Computation and Deployment
Pižurica, Nikola
Milović, Nikola
Jovančević, Igor
Heins, Conor
de Prado, Miguel
Artificial Intelligence
Active Inference (AIF) offers a robust framework for decision-making, yet its computational and memory demands pose challenges for deployment, especially in resource-constrained environments. This work presents a methodology that facilitates AIF's deployment by integrating pymdp's flexibility and efficiency with a unified, sparse, computational graph tailored for hardware-efficient execution. Our approach reduces latency by over 2x and memory by up to 35%, advancing the deployment of efficient AIF agents for real-time and embedded applications.
title A Hardware-oriented Approach for Efficient Active Inference Computation and Deployment
topic Artificial Intelligence
url https://arxiv.org/abs/2508.13177