RL Environments 筛选器。访问 huggingface.co/datasets?other=rl-environment。所有带有 rl-environment 标签的数据集均显示于此，无论其兼容何种框架。每个框架标签会在数据集页面显示该框架的图标，并在“使用此数据集”部分添加生成的代码片段。

The RL Environments filter. Go to huggingface.co/datasets?other=rl-environment. Every dataset with the rl-environment tag appears there, whatever framework it works with. Each framework tag puts the framework's icon on the dataset page and adds a generated snippet to Use this dataset.

RL Environments 筛选器。访问 huggingface.co/datasets?other=rl-environment。所有带有 rl-environment 标签的数据集都会显示在此处，无论其适配何种框架。每个框架标签都会在数据集页面显示该框架的图标，并在“Use this dataset”部分添加生成的代码片段。一个数据集可以携带多个框架标签，这正是设计初衷。标签描述的是兼容性，而兼容性并非互斥关系。所列出的每个框架必须支持仓库中的文件；添加标签并不会自动转换文件格式。请根据你使用的框架选择示例，并在独立的 Python 环境中运行，需满足下文列出的前置条件。Harbor 可以从 Hub 仓库加载任务目录。oracle agent 会运行任务的参考解决方案，随后由 verifier 对结果进行评分。此过程不调用模型。viewer 会显示任务的奖励值、verifier 输出以及日志。这有助于你在尝试模型 agent 之前检查任务及其参考解决方案。verifiers v1 的 Harbor 集成可以在不同的运行时环境（如 Docker）中运行相同的任务目录。它还支持多种 harness，包括极简的 bash harness。如果奖励值为 None，表示未产生 verifier 奖励；在将运行结果解读为模型失败之前，请先检查 error 信息。此路径预期使用 Harbor 任务目录。这一方案的优势在于，它提供了一个统一的仓库和一个讨论区，人们可以在此报告来自所有主流框架的故障任务。因此，当作者修复了一个错误的测试用例后，所有框架在下一次拉取时都能获得该修复。这就是整个集成流程。请保留 rl-environment 标签，然后列出所有能够加载你文件的框架。如果你的环境与某个我们尚未注册的框架兼容，请向受支持库列表提交 PR。我们已经提交了 PR，为一些用户已在训练的环境添加标签。如果你维护这些环境之一，合并该 PR 后，你的环境就会出现在筛选器中。

The RL Environments filter. Go to huggingface.co/datasets?other=rl-environment. Every dataset with the rl-environment tag appears there, whatever framework it works with. Each framework tag puts the framework's icon on the dataset page and adds a generated snippet to Use this dataset. A dataset can carry more than one framework tag. That is the point. Tags describe compatibility, and compatibility is not exclusive. Each listed framework must support the files in the repository; adding a tag does not convert them. Choose the example for your framework and run it in a separate Python environment with the prerequisites listed below. Harbor can load task directories from a Hub repository. The oracle agent runs the task's reference solution, then the verifier scores the result. It does not call a model. The viewer shows the task's reward, verifier output, and logs. This checks the task and its reference solution before you try a model agent. The Harbor integration of verifiers v1 can run the same task directories in different runtimes, such as Docker. It also supports different harnesses, including a minimal bash harness. A reward of None means no verifier reward was produced; inspect error before interpreting the run as a model failure. This path expects Harbor task directories. The best part is that this gives one repo and one discussion tab where people report broken tasks from all major frameworks. So when an author fixes a bad test, every framework gets the fix on the next pull. That is the whole integration. Keep rl-environment, then list every framework that can load your files. If your environment works with a framework we have not registered yet, open a PR to the list of supported libraries. We opened PRs to tag some of the environments people already train on. If you maintain one of these, merge the PR and your environment shows up in the filter.