d-tiapkin/gflownet-rl

Repository for "Generative Flow Networks as Entropy-Regularized RL" (AISTATS-2024, Oral)

26
/ 100
Experimental

This project provides an experimental framework for researchers to explore and develop advanced methods for generating diverse sets of outputs, such as molecules or abstract 'hypergrid' structures. It takes defined rules for how to build these outputs and produces various potential candidates. This is primarily for machine learning researchers and scientists working on generative models and reinforcement learning applications.

No commits in the last 6 months.

Use this if you are a machine learning researcher developing or evaluating new generative modeling techniques, particularly those based on Generative Flow Networks or entropy-regularized reinforcement learning.

Not ideal if you are an end-user looking for a ready-to-use tool to generate specific types of data without deep knowledge of machine learning algorithms.

generative-modeling reinforcement-learning-research drug-discovery-research algorithm-development computational-chemistry
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

40

Forks

1

Language

Python

License

MIT

Last pushed

Apr 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/d-tiapkin/gflownet-rl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.