Welcome RL Environments to the hub
An environment gives an agent a task, responds to its actions with observations, and scores the outcome.
Key points
- For an introduction to this interaction loop, see our blogpost on environments.
- In this release, we are focusing on the tasksets.
- An RL environment on the Hub is a dataset repo that shows up in the new RL Environments filter.
- Custom hubs, runtime registries, independent task datasets, or a GitHub list of tasks with a custom loader.
Sources (1)
- [1]Welcome RL Environments to the hubHugging Face Blog · Sep 28, 12:00 AM
An environment gives an agent a task, responds to its actions with observations, and scores the outcome.
For an introduction to this interaction loop, see our blogpost on environments.
Extractive summary: sentences quoted from the sources.