Neural Simulation-Based Inference R package neuralsbi version 0.3.2 A native R implementation of neural simulation-based inference, focused on Neural Posterior Estimation. Given a prior over parameters and a simulator, 'neuralsbi' trains a conditional neural density estimator to approximate the Bayesian posterior, enabling amortized, likelihood-free inference. Neural estimators run on the 'torch' back end. It targets applied researchers who want an approachable interface with sensible defaults and built-in posterior diagnostics. Software Depends: R (>= 4.1.0) Imports: stats, utils Suggests: torch (>= 0.11.0), testthat (>= 3.0.0), knitr, rmarkdown Pedro Nascimento de Lima <plima@rand.org> Comprehensive R Archive Network (CRAN) Pedro Nascimento de Lima [aut, cre] (ORCID: <https://orcid.org/0000-0001-9057-198X>) MIT + file LICENSE (https://CRAN.R-project.org/package=neuralsbi/LICENSE) 2026-08-03 application/tgz https://CRAN.R-project.org/package=neuralsbi doi:10.32614/CRAN.package.neuralsbi