piwheels

minari

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

Installation

In a virtualenv (see these instructions if you need to create one):

pip3 install minari

Dependencies

• typing-extensions
• packaging
• gymnasium
• numpy
• typer

Releases

Version	Released	Bullseye Python 3.9	Bookworm Python 3.11	Trixie Python 3.13	Files
0.5.3	2025-04-17
minari-0.5.3-py3-none-any.whl (55 KB)
0.5.2	2024-12-09
minari-0.5.2-py3-none-any.whl (54 KB)
0.5.1	2024-10-09
minari-0.5.1-py3-none-any.whl (50 KB)
0.5.0	2024-08-29
minari-0.5.0-py3-none-any.whl (50 KB)
0.4.3	2024-01-27
minari-0.4.3-py3-none-any.whl (42 KB)
0.4.2	2023-10-09
minari-0.4.2-py3-none-any.whl (38 KB)
0.4.1	2023-07-19
minari-0.4.1-py3-none-any.whl (38 KB)
0.4.0	2023-07-19
minari-0.4.0-py3-none-any.whl (38 KB)
0.3.1	2023-05-19
minari-0.3.1-py3-none-any.whl (30 KB)
0.3.0	2023-05-17
minari-0.3.0-py3-none-any.whl (30 KB)
0.3.0b0 pre-release	2023-05-17
minari-0.3.0b0-py3-none-any.whl (30 KB)
0.2.1	2023-01-03
0.2.0	2023-01-03
0.0.1	2022-11-14
minari-0.0.1-py3-none-any.whl (5 MB)

Issues with this package?

• Search issues for this package
• Package or version missing? Open a new issue
• Something else? Open a new issue