https://github.com/1qb-information-technologies/cool
Controlled Online Optimization Learning (COOL): Finding the Ground State of Spin Hamiltonians with Reinforcement Learning (arXiv:2003.00011)
Science Score: 10.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org, zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (15.5%) to scientific vocabulary
Repository
Controlled Online Optimization Learning (COOL): Finding the Ground State of Spin Hamiltonians with Reinforcement Learning (arXiv:2003.00011)
Basic Info
- Host: GitHub
- Owner: 1QB-Information-Technologies
- License: gpl-3.0
- Language: C
- Default Branch: master
- Size: 1.33 MB
Statistics
- Stars: 9
- Watchers: 3
- Forks: 4
- Open Issues: 1
- Releases: 0
Metadata Files
README.md
Controlled Online Optimization Learning (COOL): Finding the ground state of spin Hamiltonians with reinforcement learning
Building
You must compile the Simulated Annealing backend (written in C++) before using the gym environment.
These instructions were made using a fresh Ubuntu 18.04 installation, with Anaconda 2020.02 (Python 3.7) installed. Anaconda can be obtained from https://www.anaconda.com/distribution/.
Linux (Debian)
Install dependencies and build the Python interface to the Simulated Annealing backend:
bash
apt install swig g++ libtclap-dev libboost-dev
make install
Mac OS X
This package should work on a Mac, but dependencies are more difficult to satisfy. You will probably need to edit setup.py to manually point to your boost include paths, tclap, etc. On Linux it just works (with apt).
Examples
Example experiments relevant to the COOL manuscript are included in experiments/. The README examples for these experiments use the COOL_HOME environment variable. It's not necessary, but helpful to define this. This is the top level directory of this repository.
bash
export COOL_HOME=/home/user/git/COOL/
If you wish to run the examples (reinforcement learning code), you will need to install the Python dependencies.
bash
pip install stable-baselines
conda install tensorflow-gpu=1.13
Research paper:
Note:
environment.yml is a list of the developer's Python environment used during development. It contains more software than is required, but can be manually consulted for package version numbers, should the need arise. Most users will not need this file.
Owner
- Name: 1QBit
- Login: 1QB-Information-Technologies
- Kind: organization
- Location: Vancouver, BC
- Website: https://1qbit.com
- Repositories: 2
- Profile: https://github.com/1QB-Information-Technologies
GitHub Events
Total
- Watch event: 1
Last Year
- Watch event: 1
Dependencies
- absl-py ==0.7.1
- argparse ==1.4.0
- astor ==0.8.0
- atari-py ==0.1.15
- bleach ==3.1.0
- chardet ==3.0.4
- cloudpickle ==1.2.1
- cycler ==0.10.0
- docutils ==0.14
- future ==0.17.1
- gast ==0.2.2
- grpcio ==1.21.1
- gym ==0.12.5
- idna ==2.8
- inflect ==2.1.0
- joblib ==0.13.2
- kiwisolver ==1.1.0
- matplotlib ==3.1.0
- mpi4py ==3.0.2
- networkx ==2.3
- opencv-python ==4.1.0.25
- pandas ==0.24.2
- pillow ==6.0.0
- pip ==19.1.1
- pkginfo ==1.5.0.1
- progressbar ==2.5
- protobuf ==3.8.0
- pyglet ==1.3.2
- pyparsing ==2.4.0
- pytz ==2019.1
- readme-renderer ==24.0
- regex ==2019.6.8
- requests ==2.22.0
- requests-toolbelt ==0.9.1
- scipy ==1.3.0
- six ==1.12.0
- termcolor ==1.1.0
- tqdm ==4.32.1
- twine ==1.13.0
- urllib3 ==1.25.3
- webencodings ==0.5.1
- gym *
- numpy *