grahamannett/Minari

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Minari is a Python library for conducting research in offline reinforcement learning, akin to an offline version of Gymnasium or an offline RL version of HuggingFace's datasets library. This library is currently in beta.

The documentation website is at minari.farama.org. We also have a public discord server (which we use for Q&A and to coordinate development work) that you can join here: https://discord.gg/bnJ6kubTg6.

Note: Minari was previously developed under the name Kabuki.

Installation

To install Minari from PyPI:

pip install minari

Note that currently Minari is under a beta release. If you'd like to start testing or contribute to Minari please install this project from source with:

git clone https://github.com/Farama-Foundation/Minari.git
cd Minari
pip install -e .

Getting Started

For an introduction to Minari, see Basic Usage. To create new datasets using Minari, see our Pointmaze D4RL Dataset tutorial, which re-creates the Maze2D datasets from D4RL.

API

To check available remote datasets:

import minari

minari.list_remote_datasets()

To check available local datasets:

import minari

minari.list_local_datasets()

To download a dataset:

import minari

minari.download_dataset("door-cloned-v1")

To load a dataset:

import minari

dataset = minari.load_dataset("door-cloned-v1")

Project Maintainers

Main Contributors: Rodrigo Perez-Vicente, Omar Younis, John Balis

Maintenance for this project is also contributed by the broader Farama team: farama.org/team.

---

Minari is a shortening of Minarai, the Japanese word for "learning by observation".