Skip to main content

Python API with evolutionary computation and reinforcement learning algorithms for Khepera simulation engine

Project description

KhepPy

KhepPy stands for Khepera Python and is Python API with evolutionary computation and reinforcement learning algorithms for Khepera simulation engine. More information about the engine itself can be found here.

The idea behind KhepPy is to provide algorithms able to generate high-quality steering programs for Khepera robots.

Getting started

The procedure to run KhepPy is fast and very easy.

Prerequisites

Python requirements

  • Python 3
  • NumPy
  • (in future) Tensorflow

Khepera simulation engine binaries

Build from source: project page.
Or use precompiled binaries:

  • Linux (tested on Ubuntu 14.04)
  • OS X/macOS (tested on macOS Sierra/High Sierra)
  • Windows (tested on Windows 7/8)

Installing

  1. Download or clone this repository to local directory of your choice.
  2. Add main project directory to PYTHONPATH if you want to use KhepPy in external projects.
    export PYTHONPATH="${PYTHONPATH}:/your/directory/kheppy"
    
    Alternatively, place main project directory in site-packages.
  3. Configure KHEPERA_LIB environment variable to point to Khepera simulation engine binaries.
    export KHEPERA_LIB="/your/path/to/the/engine"
    
    If you use PyCharm, go to Run > Edit Configurations... and add KHEPERA_LIB variable to Environment variables list.

Test installation

For basic verification run:

python -c 'from kheppy.core import Simulation'

No output means kheppy.core should be ready to use.

Examples

Now you can run some examples to familiarize yourself with KhepPy.

License

This project is licensed under the MIT License - see the LICENSE.txt file for details

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kheppy-0.1.0.tar.gz (15.4 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page