AI updates
Hugging Face Hub adds RL environments
The Hugging Face Hub gained a filter for RL environments: an environment is a dataset repo (tasks, tests, containers and a reward rule) with a "Use this dataset" command for frameworks like Harbor, Verifiers and NVIDIA NeMo Gym.
- The post argues an environment is just data (tasks, tests, containers, reward rule) plus a runtime, so it doesn't need a separate registry.
- No new repo type: environments are dataset repos that appear under an RL Environments filter.