Skip to content

sintefneodroid/neo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

header

Neo

Neo is a python package that enables deserialisation, serialisation and an interface to the Droid counterpart of the Neodroid platform.


Neodroid is developed with support from Research Council of Norway Grant #262900. (https://www.forskningsradet.no/prosjektbanken/#/project/NFR/262900)


Build Status Coverage Status GitHub Issues Documentation Status
GitHub Forks GitHub Stars GitHub License Python 3
Pypi Version Pypi Downloads Pypi Wheel Updates

python flatbuffers pyzmq

Installation

pip3 install -U neodroid

Usage

import neodroid as neo

Examples

We have included some example applications in this repository.

Observation Generator

Random Agent

Curriculum

An Example Implementation Of Using An Interface

The application displays data received from the example application of the Droid project repository. neo

To Do's

  • Be able to select and/or parameterise an objective/evaluation (None,ReachGoal,Stabilise,..) function for an environment

Contributing

See guidelines for contributing here.

Licensing

This project is licensed under the Apache V2 License. See LICENSE for more information.

Citation

For citation you may use the following bibtex entry:

@misc{neodroid,
  author = {Heider, Christian},
  title = {Neodroid Platform},
  year = {2018},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/sintefneodroid}},
}

Other Components Of the Neodroid Platform

FAQ

  • My iterations per second are maxed out at ~60..
    • Ensure that you have disabled vsync, for bumblebee users on linux you can use vblank_mode=0 optirun ...
  • Why was this tool created, what does it serve and not just use Unity's own RL framework?
    • This project is very similar to Unity's own project Unity Machine Learning Agents. The most of the efforts done in this project were made prior to their announcement, Introducing: Unity Machine Learning Agents. The entire Neodroid platform served and still serves as a tool for academic research specific to the authors interests, hence explaining to the existence and future direction of this project.

Other Problems

Please contact us or add an issue if have a problem that is not listed in the FAQ

Authors

Here other contributors to this project are listed.