Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/devsisters/neural-combinatorial-rl-tensorflow
in progress
https://github.com/devsisters/neural-combinatorial-rl-tensorflow
Last synced: about 2 months ago
JSON representation
in progress
- Host: GitHub
- URL: https://github.com/devsisters/neural-combinatorial-rl-tensorflow
- Owner: devsisters
- License: mit
- Created: 2017-01-07T06:00:50.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2017-06-11T14:43:25.000Z (over 7 years ago)
- Last Synced: 2024-03-17T02:42:14.368Z (10 months ago)
- Language: Python
- Homepage:
- Size: 57.6 KB
- Stars: 106
- Watchers: 15
- Forks: 27
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Neural Combinatorial Optimization in Tensorflow
TensorFlow implementation of [Neural Combinatorial Optimization with Reinforcement Learning](http://arxiv.org/abs/1611.09940).
![model](./assets/model.png)
(in progress)
## Requirements
- Python 2.7
- [tqdm](httsp://github.com/tqdm/tqdm)
- [TensorFlow 0.12.1](httsp://github.com/tensorflow/tensorflow/tree/r0.12)## Usage
To train a model:
$ python main.py --task=tsp20 --lr_start=0.001 --min_data_length=5 --max_data_length=20
$ python main.py --task=tsp50 --lr_start=0.001 --min_data_length=5 --max_data_length=50
$ python main.py --task=tsp100 --lr_start=0.0001 --min_data_length=5 --max_data_length=100To train a model:
$ python main.py
$ tensorboard --logdir=logs --host=0.0.0.0To test a model:
$ python main.py --is_train=False
## Results
(in progress)
## Author
Taehoon Kim / [@carpedm20](http://carpedm20.github.io)