torchgfn: A PyTorch GFlowNet library

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Viviano, Joseph D., Younis, Omar G., Choi, Sanghyeok, Schmidt, Victor, Bengio, Yoshua, Lahlou, Salem
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910060310953984
author Viviano, Joseph D.
Younis, Omar G.
Choi, Sanghyeok
Schmidt, Victor
Bengio, Yoshua
Lahlou, Salem
author_facet Viviano, Joseph D.
Younis, Omar G.
Choi, Sanghyeok
Schmidt, Victor
Bengio, Yoshua
Lahlou, Salem
contents The growing popularity of generative flow networks (GFlowNets or GFNs) from 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/).
format Preprint
id arxiv_https___arxiv_org_abs_2305_14594
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle torchgfn: A PyTorch GFlowNet library
Viviano, Joseph D.
Younis, Omar G.
Choi, Sanghyeok
Schmidt, Victor
Bengio, Yoshua
Lahlou, Salem
Machine Learning
The growing popularity of generative flow networks (GFlowNets or GFNs) from 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/).
title torchgfn: A PyTorch GFlowNet library
topic Machine Learning
url https://arxiv.org/abs/2305.14594