tinker495/JAxtar
JAxtar is a project with a JAX-native implementation of parallelizeable A* & Q* solver for neural heuristic search research.
JAxtar helps machine learning researchers quickly find optimal paths or solutions for complex puzzles and problems using advanced search algorithms. It takes in initial problem states and desired target states, often leveraging neural network heuristics, to efficiently output the shortest or lowest-cost sequence of actions. This tool is for researchers developing and testing new AI agents, especially those focused on graph search and reinforcement learning in challenging, high-dimensional environments.
Use this if you are a machine learning researcher working on AI problems that require high-performance, GPU-accelerated pathfinding or solution discovery for complex state spaces.
Not ideal if you are looking for a simple, off-the-shelf pathfinding solution for basic 2D grids or if your research does not involve deep learning frameworks like JAX.
Stars
44
Forks
4
Language
Python
License
MIT
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tinker495/JAxtar"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/