# Hugging Face — Welcome RL Environments to the hub

- Company: Hugging Face (huggingface.co)
- Announced: 2026-09-28
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://huggingface.co/blog/rl-environments
- Record: https://forck.live/items/16043-welcome-rl-environments-to-the-hub
- Subject: Platform

Hugging Face Hub added a dedicated section for reinforcement learning environments, letting dataset repositories be tagged as RL environments and run through supported frameworks. The release includes an RL Environments filter, framework tags for four environments, and integrations with Harbor and NeMo Gym for running tasks and inspecting rewards.

## Evidence

Verbatim from https://huggingface.co/blog/rl-environments:

> An RL environment on the Hub is a dataset repo that shows up in the new RL Environments filter. The Use this dataset button gives you the command to run it in that framework.

---

Record: https://forck.live/items/16043-welcome-rl-environments-to-the-hub
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md