Stop building environment registries What shipped Run an environment and inspect its reward Harbor: run a reference solution Verifiers: run a model on the same task OpenEnv: run an agent and inspect its reward NeMo Gym: generate responses and inspect rewards Tag your environment Already on the Hub What comes next Reinforcement Learning environments give new capabilities to agentic AI systems, and they’re a great way to measure and improve performance in your agents. Therefore, Hugging Face Hub now has a special place for RL Environments.
An environment gives an agent a task, responds to its actions with observations, and scores the outcome. The resulting rewards can measure an agent's performance during evaluation or provide a learning signal during training. For an introduction to this interaction loop, see our blogpost on environments. Within the environment, the agent will perform a set of tasks that are represented as datasets. Therefore, environments can be split into broadly two parts: tasksets and runtimes. In this release, we are focusing on the tasksets.
