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.
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.
Installation
To install Minari from PyPI:
pip install minari
This will install the minimum required dependencies. Additional dependencies will be prompted for installation based on your use case. To install all dependencies at once, use:
pip install "minari[all]"
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 --single-branch
cd Minari
pip install -e ".[all]"
Command Line API
To check available remote datasets:
minari list remote
To download a dataset:
minari download D4RL/door/human-v2
To check available local datasets:
minari list local
To show the details of a dataset:
minari show D4RL/door/human-v2
For the list of commands:
minari --help
Basic Usage
Reading a Dataset
import minari
dataset = minari.load_dataset("D4RL/door/human-v2")
for episode_data in dataset.iterate_episodes():
observations = episode_data.observations
actions = episode_data.actions
rewards = episode_data.rewards
terminations = episode_data.terminations
truncations = episode_data.truncations
infos = episode_data.infos
...
Writing a Dataset
import minari
import gymnasium as gym
from minari import DataCollector
env = gym.make('FrozenLake-v1')
env = DataCollector(env)
for _ in range(100):
env.reset()
done = False
while not done:
action = env.action_space.sample() # <- use your policy here
obs, rew, terminated, truncated, info = env.step(action)
done = terminated or truncated
dataset = env.create_dataset("frozenlake/test-v0")
For other examples, see Basic Usage. For a complete tutorial on how to create new datasets using Minari, see our Pointmaze D4RL Dataset tutorial, which re-creates the Maze2D datasets from D4RL.
Training Libraries Integrating Minari
Citation
If you use Minari, please consider citing it:
@software{minari,
author = {Younis, Omar G. and Perez-Vicente, Rodrigo and Balis, John U. and Dudley, Will and Davey, Alex and Terry, Jordan K},
doi = {10.5281/zenodo.13767625},
month = sep,
publisher = {Zenodo},
title = {Minari},
url = {https://doi.org/10.5281/zenodo.13767625},
version = {0.5.0},
year = 2024,
bdsk-url-1 = {https://doi.org/10.5281/zenodo.13767625}
}
Minari is a shortening of Minarai, the Japanese word for "learning by observation".
Metadata
Release files for minari 0.5.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| minari-0.5.4.tar.gz | 52.5 kB | Without provenance | Details for minari-0.5.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| minari-0.5.4-py3-none-any.whl | Python 3 | none | any | Details for minari-0.5.4-py3-none-any.whl |
Total release size: 109.2 kB
Release files / minari-0.5.4.tar.gz
| Download URL | minari-0.5.4.tar.gz |
|---|---|
| Size | 52.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a32a7c7a93b6986ceac3552c32cecd94e37367cdb533a81647ca9e76b5b42116
|
|
BLAKE2b-256 checksum How to use checksums |
0a18523f8a6da59568691b4de8924177bf62a913b57eacf0b49f518a4d7d54c8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.4
|
Release files / minari-0.5.4-py3-none-any.whl
| Download URL | minari-0.5.4-py3-none-any.whl |
|---|---|
| Size | 56.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c396ca5d141a519aaa60d15e5f7f73487d6084e5bb00acd08b63a01f65eefd69
|
|
BLAKE2b-256 checksum How to use checksums |
54578abdaf14f018f987798a8d30df2e75d4515e666552c2e6b57f2bda76c268
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.4
|
Security for minari 0.5.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.