Welcome to Flai, pronounced as 'Fly!' 😃
Flai is toolkit for developing and comparing reinforcement learning algorithms built by deepair. It is inspired by OpenAI Gym and has been modified for travel's needs. Flai comes with pre packaged games that are designed to play by reinforcement learning agents. We are continuously developing and adding new environments to Flai.
To install the entire library, use pip install deepair-flai.
This does not include dependencies for all families of environments (there's a massive number, and some can be problematic to install on certain systems). You can install these dependencies for one family like pip install deepair-flai[seatsmart] or use pip install deepair-flai[ubundle] to install all dependencies.
We support Python 3.8 and above on Linux and macOS. We will accept PRs related to Windows, but do not officially support it.
Coming soon..
Check out our documentation site here.
Note: Documentation is work in progress. Please feel free to raise issues or contribute to enhance the experience.
Launching documentation server locally requires npm. It is built on docsify and recommended to install globally using the following command:
npm i docsify-cli -g
Now to run the server, you can run the following command:
docsify init ./docs