This is a third-party implementation of Neural A* search [Yonetani+, ICML 2021]. I have reimplemented the Neural A* model and training scripts in JAX and Flax, and expect an overall speedup thanks to JAX's jit compile and vmapping.
This codebase is under active development; the quantitative performance is still limited due to potential bugs and implementation differences between PyTorch and JAX.
The code has been tested on Ubuntu >=18.04 as well as WSL2 (Ubuntu 20.04) on Windows 11, with python3 (>=3.8). Planning can be performed only on the CPU, and the use of GPUs is supported for training/evaluating Neural A* models. We also provide Dockerfile and docker-compose.yaml to replicate our setup.
$ git clone --recursive https://github.com/yonetaniryo/neural-astar-jax.git
$ python -m venv .venv
$ source .venv/bin/activate
(.venv) $ pip install .[dev]
@InProceedings{pmlr-v139-yonetani21a,
title = {Path Planning using Neural A* Search},
author = {Ryo Yonetani and
Tatsunori Taniai and
Mohammadamin Barekatain and
Mai Nishimura and
Asako Kanezaki},
booktitle = {Proceedings of the 38th International Conference on Machine Learning},
pages = {12029--12039},
year = {2021},
editor = {Meila, Marina and Zhang, Tong},
volume = {139},
series = {Proceedings of Machine Learning Research},
month = {18--24 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v139/yonetani21a/yonetani21a.pdf},
url = {http://proceedings.mlr.press/v139/yonetani21a.html},
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent