Data

Tools

Indexes

Applications

Experiments

Open Source Science

tjc-gym

OpenAI Gym environment of Traffic Junction with continuous action space

https://github.com/jakobdybdahl/tjc-gym

Science Score: 54.0%

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

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.6%) to scientific vocabulary
Last synced: 7 months ago · JSON representation ·

Repository

OpenAI Gym environment of Traffic Junction with continuous action space

Basic Info
  • Host: GitHub
  • Owner: jakobdybdahl
  • Language: Python
  • Default Branch: main
  • Size: 37.1 KB
Statistics
  • Stars: 7
  • Watchers: 2
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created over 4 years ago · Last pushed about 4 years ago
Metadata Files
Readme Citation

README.md

tjc-gym

Traffic Juntion Continuous (tjc) is a continuous version of the environment Traffic Junction defined in Learning Multiagent Communication with Backpropagation. The environment is based on OpenAI Gym and has an continouos observation and action space where the original is discrete.

Installation

Through PyPi:

bash pip install tjc-gym

Or directly by cloning repo:

bash git clone https://github.com/jakobdybdahl/tjc-gym.git cd tjc-gym pip install -e .

Usage

```python import gym

env = gym.make('tjcgym:TrafficJunctionContinuous6-v0') done = [False] * env.nagents score = 0

obs = env.reset() while not all(done): env.render() actions = [acsp.sample() for acsp in env.actionspace] obs, rewards, done, info = env.step(actions) score += sum(rewards)

```

Reference

If you want to site our work, please see the citation file in the repo for details. Through GitHub it is possible to 'Cite this repository' and get a BibTeX reference - it can be found in the 'About' section of this repo.

Acknowledgement

This environment was developed by RasmusThorsen and jakobdybdahl to complement our master thesis at @ Aarhus University.

Owner

  • Name: Jakob Dybdahl
  • Login: jakobdybdahl
  • Kind: user
  • Location: Aarhus, Denmark

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  tjc-gym: Traffic Junction Continuous OpenAI Gym
  Environment
message: >-
  If you would like to cite our work, please use this
  information.
type: software
authors:
  - given-names: Jakob
    family-names: Dybdahl
    email: dybdahl@smukand.dk
  - given-names: Rasmus
    family-names: Thorsen
    email: rallethor@hotmail.com
repository-code: 'https://github.com/jakobdybdahl/tjc-gym'
license: MIT
version: 0.0.1
date-released: '2021-12-11'

GitHub Events

Total
Last Year

Committers

Last synced: about 3 years ago

All Time
  • Total Commits: 41
  • Total Committers: 2
  • Avg Commits per committer: 20.5
  • Development Distribution Score (DDS): 0.195
Top Committers
Name Email Commits
Jakob Dybdahl d****l@s****k 33
Rasmus Østergaard Thorsen r****t@i****k 8
Committer Domains (Top 20 + Academic)
it-minds.dk: 1 smukand.dk: 1

Issues and Pull Requests

Last synced: 7 months ago

All Time
  • Total issues: 0
  • Total pull requests: 2
  • Average time to close issues: N/A
  • Average time to close pull requests: about 11 hours
  • Total issue authors: 0
  • Total pull request authors: 2
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 0
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
Pull Request Authors
  • jakobdybdahl (1)
  • RasmusThorsen (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 20 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 6
  • Total maintainers: 1
pypi.org: tjc-gym

OpenAI Gym environment of Traffic Junction with continuous action space

  • Versions: 6
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 20 Last month
Rankings
Dependent packages count: 10.0%
Stargazers count: 19.3%
Average: 20.3%
Dependent repos count: 21.7%
Forks count: 22.6%
Downloads: 27.6%
Maintainers (1)
jakobdybdahl
Last synced: 7 months ago

Dependencies

setup.py pypi
  • gym ==0.21.0