Hugging Face Hub adds a home for reinforcement learning environments
Hugging Face added an RL Environments filter to the Hub so agent training and evaluation environments can be shared as dataset repos. It works with frameworks including Harbor, Verifiers, OpenEnv and NVIDIA NeMo Gym.
Hugging Face announced on September 28 that the Hub now has a dedicated place for reinforcement learning environments, which give an agent a task, respond to its actions and score the outcome.
An environment on the Hub is a regular dataset repo that appears under a new RL Environments filter, with a Use this dataset button that gives the command to run it in a supported framework. Hugging Face says there is no new repo type, registry or sign-up, and that this first release focuses on tasksets.