torchgfn: A PyTorch GFlowNet Library
Joseph D. Viviano, Omar G. Younis, Sanghyeok Choi, Victor Schmidt, Yoshua Bengio, Salem Lahlou; 27(142):1−15, 2026.
Abstract
The growing popularity of generative flow networks (GFlowNets or GFNs) among a range of researchers with diverse backgrounds and areas of expertise necessitates a library that facilitates the testing of new features (e.g., training losses and training policies) against standard benchmark implementations, or on a set of common environments. We present torchgfn, a PyTorch library that aims to address this need. Its core contribution is a modular and decoupled architecture which treats environments, neural network modules, and training objectives as interchangeable components. This provides users with a simple yet powerful API to facilitate rapid prototyping and novel research. Multiple examples are provided, replicating and unifying published results. The library is available on GitHub (https://github.com/GFNOrg/torchgfn) and on PyPI (https://pypi.org/project/torchgfn/).
[abs]
[pdf][bib] [code]| © JMLR 2026. (edit, beta) |