PyPI page
Home page
Author:
Glenn Nadeau
Summary:
Turn any real software into a trainable, gradable, replayable RL environment for AI agents.
Latest version:
0.2.0
Optional dependencies:
accelerate
|
datasets
|
peft
|
pytest
|
pytest-cov
|
transformers
|
trl
Downloads last day:
0
Downloads last week:
4
Downloads last month:
103
7-day smoothing