Training a coding model to paint watercolours with TRL and OpenEnv

Automated excerpt

Three runs, one per reward mix, evolving in parallel. The pairwise judge is Qwen3-VL-30B-A3B-Instruct, a general vision model called through HF Inference Providers. Three experiments on the reward, three flat lines. Same base model, same pool, three reward mixes, three styles. You can judge for yourself in the gallery, which has every painting of every run, sortable by step and by reward.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.