update the baseline for new envs? [feature request]

araffin / rl-baselines-zoo

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

https://stable-baselines.readthedocs.io/

MIT License

1.12k stars 206 forks source link

Closed MartinaRuocco closed 3 years ago

MartinaRuocco commented 3 years ago

Hi, thank you for this project!

I'd like to suggest you update this baseline with some new Robotic envs, such as

it would also be cool to develop the Gym Environments for the pybullet_robots such as:

but I know that this is not the purpose of this project.

araffin commented 3 years ago

FetchSlideEnv (MuJoCo)

This requires a license but I would be open to merge a PR with a trained agent (as in #53 ).

Panda and iCub (PyBullet)

This project is still in alpha. But you can use it by customising slightly the rl zoo (or passing --gym-packages, cf example in the README).

it would also be cool to develop the Gym Environments for the pybullet_robots such as:

We do not provide environment, only training code/structure for them.