AI & ML interests

RL Environments at Scale

Recent Activity

AdithyaSKย  updated a model 14 minutes ago
HuggingEnvs/geoguesser-qwen3.5-4b-grpo-v3
AdithyaSKย  published a model 14 minutes ago
HuggingEnvs/geoguesser-qwen3.5-4b-grpo-v3
AdithyaSKย  updated a bucket about 15 hours ago
HuggingEnvs/geoguesser-grpo-v2-trackio-bucket
View all activity

sergiopaniegoย 
posted an update 1 day ago
view post
Post
898
Can you do RL over taste?

I've spent some time reproducing, in the open, Surya N's idea of training a model to paint with code. It's a coding model that learns to paint watercolours by writing JS code, trained with GRPO. I used TRL and OpenEnv for this, with the whole pipeline running on Hugging Face.

The interesting part is that the reward has no correct answer, unlike a math problem. In this case it's based on the artistic preferences of the person who builds the dataset.

Everything is published: the environment, the reference pool, the trained adapters, every painting of every run with the code that made it, and a write-up with all the decisions, including the ones that went wrong.

Blog post: https://huggingface.co/blog/train-to-paint-with-code