hi-abhi/tensorflow-value-iteration-networks

TensorFlow implementation of the Value Iteration Networks (NIPS '16) paper

50
/ 100
Established

This project helps machine learning researchers and developers explore and implement Value Iteration Networks (VINs). It takes GridWorld datasets (or similar structured spatial data) as input and produces a trained model capable of predicting optimal paths or actions in environments where planning is crucial. It is primarily for those working on advanced AI algorithms for decision-making in complex environments.

552 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or developer interested in experimenting with or building upon Value Iteration Networks for tasks requiring integrated perception and planning.

Not ideal if you are looking for a plug-and-play solution for a specific navigation or planning problem without needing to understand or modify the underlying deep learning model.

reinforcement-learning path-planning deep-learning-research autonomous-navigation algorithmic-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

552

Forks

118

Language

Python

License

Apache-2.0

Last pushed

Mar 07, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hi-abhi/tensorflow-value-iteration-networks"

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