Edward Beeching

We have tutorials on the HF hub [here](https://huggingface.co/course/chapter4/1). If you are able to convert the checkpoints to StableBaselines3 models, we include a a push_to_hub() function in our [hugging_face_sb3 fork](https://github.com/huggingface/huggingface_sb3). I...

Thanks for such a positive comment and first issue. Regarding model export, currently the model is always hosted in python, which means python is a dependency. But this is one...

> hmm thanks for the response! Wel When I was looking for How to implement Reiforcement Learning, I was looking for a C++ implementation, because then I could make as...

Hi, For the 12k interactions it was running 4 parallel environments with 16 agents instatiated inside each env and action repeat of 4. For both Godot and Unity, one of...

Hi. I actually had exactly the sample problem as you and I never managed to resolve it. There are Godot RL frameworks that use the torch c++ library see [GodotAIGym](https://lupoglaz.github.io/GodotAIGym/),...

Thank you for your feedback. I assume you have followed the [examples](https://github.com/edbeeching/godot_rl_agents/blob/main/docs/EXAMPLE_ENVIRONMENTS.md) ? I am would gladly extend the examples and documentation. Do you have some specific examples of dependencies...

Thanks for your comments. I have reduced the nesting a bit and reused parts where possible. The override_defaults for the envpool of Atari and Mujoco are slightly different (batched rendering,...

@alex-petrenko, ah good. One less wrapper to maintain. I've updated everything. Good point about dev_envpool. I did the example renames as well, apart from isaacgym. I didn't touch doom subdirs,...

Hi, did you find a solution to this problem?

This issue is related to scaling, use bounds to make an object larger / smaller.