Reinforcement-learning Task Page about huggingface.js HOT 19 OPEN

Awesome, thanks, @merveenoyan! I added to my to-do list. I'll ping you if I run into problems.

from huggingface.js.

@merveenoyan I will be happy to contribute :)

from huggingface.js.

@osmanalenbey
Great!!! I'd like to briefly go through on what we want to do here 🙂 Task pages are documentation related to machine learning tasks. This is primarily aimed to educate software developers who want to simply know about the task, find a model, call a pipeline and build their first PoC. Some of the task pages are empty, some are full. The empty ones are the ones we appreciate community contributions for.
This is an example task page for text generation task: https://huggingface.co/tasks/text-generation and this is the page for RL, which is empty: https://huggingface.co/tasks/reinforcement-learning. We want community to help us fill these pages.

I explained the details in this issue: huggingface/hub-docs#369
Would you like to fill the whole task or parts of it? Note that it might be overwhelming to take over all of it so I suggest taking a couple of parts and see if this works for you.
Please let me know of any questions if you have any 🙂

from huggingface.js.

@merveenoyan hello. May I ask if you want a specific part of reinforcement learning relevant to project or any information as detailed as possible?

from huggingface.js.

@osmanalenbey These are wikipedia-like pages, so you can contribute basic information about a task. Some task pages are already full, you can take a look at the page of text-classification for inspiration: https://huggingface.co/tasks/text-classification. The list of what you can contribute is already given above.

Task description
Subtasks (if there is any)
Most used dataset for the task
Most used model for the task
Metrics that are used to evaluate the task
Libraries used for the task
Use cases
Small snippet for inference that demonstrates the task

from huggingface.js.

Hello!! I would like to contribute
can add one or two parts :)

from huggingface.js.

hello @merveenoyan can you assign me this task!!

from huggingface.js.

@utkarsh0308 yes! you can! @02shanks can you both write down what you'd like to contribute to avoid duplication of efforts 🙂

from huggingface.js.

I can work on Task description and then on Most used model for the task

from huggingface.js.

I can contribute to use cases

from huggingface.js.

@merveenoyan I can't find the reinforcement-learning folder in my fork

from huggingface.js.

#388 Added Reinforcement learning use cases

from huggingface.js.

Hi! @merveenoyan it seems that Most used dataset for the task, Metrics that are used to evaluate the task, and Libraries used for the task are still available. Can I contribute those?

from huggingface.js.

@emiliolehoucq sure! 🙂

from huggingface.js.

Hey @merveenoyan i can see the Inference and the Variants task is still open. can i contribute to those?

from huggingface.js.

@shreyansjainn yep, you can :)

from huggingface.js.

@merveenoyan great, thanks, will start working on this!!! if I can ask what is generally the timeline for these tasks? this is my first time contributing to OSS.

from huggingface.js.

@shreyansjainn feel free to take your time, we have no hurry!

from huggingface.js.

Lots of cool contributions! This is just missing the snippet now

from huggingface.js.