A modular AI agent experimentation tool.
Project description
piSTAR Lab
WARNING: Under active development - not ready for public use.
Overview
piSTAR Lab is a modular deep reinforcement learning platform built to make AI development accessible and fun.
Release: 0.0.1-dev (early release)
Documentation https://pistarlab.readthedocs.io
Features
- Web UI
- Plugin System for adding new agents, environments or tasks types
- Python API, anthing you can do in the UI, you can do in Python as well
- Run agents in single and multi player environments
- Experiment tracking
- Uses Ray Project (https://ray.io/) under the hood for distributed processing
- More to come
UI Screenshots
Quick Start
Detailed documentation is published at https://pistarlab.readthedocs.io
Notes
- Only tested on Ubuntu, but should also work on OS X. MS Windows users see Installation using Docker
- Suggest using Anaconda or Miniconda for Python installation (visit https://www.anaconda.com/products/individual for instructions)
- Requires pip and python 3.7 or 3.8
Installation
from pypi
pip install -U pistarlab[all]
from repo
git clone --single-branch --depth=1 http://github.com/pistarlab/pistarlab/
pip install -e ."[all]"
Usage
To launch piSTAR Lab UI, run:
pistarlab_launcher
Open browser to: http://localhost:7777
Contributing
We are still in an early phase of this release but if you are interested in contributing to piSTAR Lab, please reach out.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pistarlab-0.0.1.dev1.tar.gz
(11.3 MB
view hashes)
Built Distribution
Close
Hashes for pistarlab-0.0.1.dev1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 18329defdf5e2ec2f2e3654e448e690933c50bab7f199e7b29ae799f5df4efe0 |
|
MD5 | a915a022219df3fa5b2958f701f8a524 |
|
BLAKE2b-256 | 8e5079c4775930b4a73cf8fb005e9870de3e345e4a28d1727696d6ccad1425d6 |