graphenv

graphenv: a Python library for reinforcement learning on graph search spaces - Published in JOSS (2022)

https://github.com/nrel/graph-env

Science Score: 93.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 4 DOI reference(s) in README and JOSS metadata
✓
Academic publication links
Links to: joss.theoj.org, zenodo.org
○
Committers with academic emails
○
Institutional organization owner
✓
JOSS paper metadata
Published in Journal of Open Source Software

Keywords

graph-algorithms gym-environment machine-learning python ray reinforcement-learning

Keywords from Contributors

mesh

Scientific Fields

Artificial Intelligence and Machine Learning Computer Science - 33% confidence

Last synced: 4 months ago · JSON representation

Repository

Reinforcement learning for combinatorial optimization over directed graphs

Basic Info

Host: GitHub
Owner: NREL
License: bsd-3-clause
Language: Python
Default Branch: main
Homepage: https://NREL.github.io/graph-env/
Size: 8.41 MB

Statistics

Stars: 41
Watchers: 7
Forks: 9
Open Issues: 1
Releases: 18

Topics

graph-algorithms gym-environment machine-learning python ray reinforcement-learning

Created almost 4 years ago · Last pushed over 2 years ago

Metadata Files

Readme Contributing License Code of conduct Codemeta Zenodo

graph-env

The graphenv Python library is designed to 1) make graph search problems more readily expressible as RL problems via an extension of the OpenAI gym API while 2) enabling their solution via scalable learning algorithms in the popular RLLib library.

RLLib provides out-of-the-box support for both parametrically-defined actions and masking of invalid actions. However, native support for action spaces where the action choices change for each state is challenging to implement in a computationally efficient fashion. The graphenv library provides utility classes that simplify the flattening and masking of action observations for choosing from a set of successor states at every node in a graph search.

Installation

Graphenv can be installed with pip: pip install graphenv

Quick Start

graph-env allows users to create a customized graph search by subclassing the Vertex class. Basic examples are provided in the graphenv/examples folder. The following code snippet shows how to randomly sample from valid actions for a random walk down a 1D corridor:

```python import random from graphenv.examples.hallway.hallwaystate import HallwayState from graphenv.graphenv import GraphEnv

state = HallwayState(corridorlength=10) env = GraphEnv({"state": state, "maxnum_children": 2})

obs = env.makeobservation() done = False totalreward = 0

while not done: action = random.choice(range(len(env.state.children))) obs, reward, terminated, truncated, info = env.step(action) done = terminated or truncated total_reward += reward ```

Additional details on this example are given in the documentation

Documentation

The documentation is hosted on GitHub Pages

Contributing

We welcome bug reports, suggestions for new features, and pull requests. See our contributing guidelines for more details.

License

Owner

Name: National Renewable Energy Laboratory
Login: NREL
Kind: organization
Location: Golden, CO

Website: http://www.nrel.gov
Repositories: 599
Profile: https://github.com/NREL

JOSS Publication

graphenv: a Python library for reinforcement learning on graph search spaces

Published

September 05, 2022

DOI

10.21105/joss.04621

Volume 7, Issue 77, Page 4621

Authors

David Biagioni

Computational Sciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA

Charles Edison Tripp

Computational Sciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA

Struan Clark

Computational Sciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA

Dmitry Duplyakin

Computational Sciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA

Jeffrey Law

Biosciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA

Peter C. St. John

Biosciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA

Editor

Øystein Sørensen

CodeMeta (codemeta.json)

{
  "@context": "https://raw.githubusercontent.com/codemeta/codemeta/master/codemeta.jsonld",
  "@type": "Code",
  "author": [
    {
      "@id": "0000-0002-7928-3722",
      "@type": "Person",
      "email": "peter.stjohn@nrel.gov",
      "name": "Peter St. John",
      "affiliation": "Biosciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA"
    },
    {
      "@id": "0000-0001-6140-1957",
      "@type": "Person",
      "email": "Dave.Biagioni@nrel.gov",
      "name": "Dave Biagioni",
      "affiliation": "Computational Sciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA"
    },
    {
      "@id": "0000-0003-0078-6560",
      "@type": "Person",
      "email": "Struan.Clark@nrel.gov",
      "name": "Struan Clark",
      "affiliation": "Computational Sciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA"
    },
    {
      "@id": "0000-0002-5867-3561",
      "@type": "Person",
      "email": "Charles.Tripp@nrel.gov",
      "name": "Charles Tripp",
      "affiliation": "Computational Sciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA"
    },
    {
      "@id": "0000-0001-5132-0168",
      "@type": "Person",
      "email": "Dmitry.Duplyakin@nrel.gov",
      "name": "Dmitry Duplyakin",
      "affiliation": "Computational Sciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA"
    },
    {
      "@id": "0000-0003-2828-1273",
      "@type": "Person",
      "email": "Jeffrey.Law@nrel.gov",
      "name": "Jeffrey Law",
      "affiliation": "Biosciences Center, National Renewable Energy Laboratory, Golden CO 80401, USA"
    }
  ],
  "identifier": "",
  "codeRepository": "https://github.com/NREL/graph-env",
  "datePublished": "2022-07-21",
  "dateModified": "2022-07-21",
  "dateCreated": "2022-07-21",
  "description": "Reinforcement learning on directed graphs",
  "keywords": "reinforcement learning, combinatorial optimization",
  "license": "BSD 3-Clause License",
  "title": "graph-env",
  "version": "v0.0.6"
}

GitHub Events

Total

Watch event: 3
Fork event: 6

Last Year

Watch event: 3
Fork event: 6

Committers

Last synced: 5 months ago

All Time

Total Commits: 238
Total Committers: 11
Avg Commits per committer: 21.636
Development Distribution Score (DDS): 0.445

Past Year

Commits: 0
Committers: 0
Avg Commits per committer: 0.0
Development Distribution Score (DDS): 0.0

Top Committers

Name	Email	Commits
Peter St. John	p**n@g**m	132
Biagioni	d**n@n**v	27
Peter St. John	p**n@n**v	21
Jeff Law	j**w@n**v	15
Struan Clark	x****n	14
Dave Biagioni	d**i@n**v	14
ctripp	c**p@n**v	10
Dave Biagioni	d****i	2
dependabot[bot]	4****]	1
Konstantinos Mixios	k**s@g**m	1
Dmitry Duplyakin	d**n@n**v	1

Committer Domains (Top 20 + Academic)

nrel.gov: 6

Issues and Pull Requests

Last synced: 4 months ago

All Time

Total issues: 15
Total pull requests: 39
Average time to close issues: 19 days
Average time to close pull requests: about 1 month
Total issue authors: 6
Total pull request authors: 7
Average comments per issue: 1.0
Average comments per pull request: 0.46
Merged pull requests: 37
Bot issues: 0
Bot pull requests: 1

Past Year

Issues: 0
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 0
Pull request authors: 0
Average comments per issue: 0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

pstjohn (6)
osorensen (3)
davebiagioni (2)
vwxyzjn (2)
mjstahlberg (1)
sundar19 (1)

Pull Request Authors

pstjohn (27)
davebiagioni (7)
jlaw9 (2)
iammix (1)
dependabot[bot] (1)
xtruan (1)
dmdu (1)

Top Labels

Issue Labels

documentation (1)

Pull Request Labels

dependencies (1)

Dependencies

.github/workflows/build_docs.yml actions

JamesIves/github-pages-deploy-action v4.2.5 composite
actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/draft_pdf.yml actions

actions/checkout v2 composite
actions/upload-artifact v1 composite
openjournals/openjournals-draft-action master composite

.github/workflows/run_tests_and_deploy.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite
actions/setup-python v2 composite
pypa/gh-action-pypi-publish release/v1 composite

docs/requirements_for_docs.txt pypi

Sphinx ==4.5.0
ipython ==8.2.0
nbconvert ==6.5.1
nbsphinx ==0.8.8
sphinx-rtd-theme ==1.0.0

pyproject.toml pypi

setup.py pypi

devtools/conda-envs/environment.yml conda

gym
networkx
pip
pytest
pytorch
tensorflow

graphenv

Science Score: 93.0%

Keywords

Keywords from Contributors

Scientific Fields

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

graph-env

Installation

Quick Start

Documentation

Contributing

License

Owner

JOSS Publication

graphenv: a Python library for reinforcement learning on graph search spaces

Authors

Editor

Tags

CodeMeta (codemeta.json)

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Dependencies