Clarify documentation: anomaly signal explainer, GRPO scope notes

Tighten README: resolve GRPO contradiction, drop duplicate baseline table, remove internal mentor docs

Add SFT v3 + GRPO refine results to README + results.md

Post-deadline: full eval results + bigger plots via Git LFS

README: embed reward curve and belief-accuracy curve plots

README: drop iter2 plots, keep only SFT v3 loss curve (current pipeline)

README: surface headline result table at top so judges don't need to click through

Embed training plots inline in README with captions

Add plots/ folder: SFT v3 loss + GRPO iter2 reward curves

Move blog to root as BLOG.md (per Meta mentor guidance)

Prune internal/stale docs; sharpen README submission links

Fix max_new_tokens for CoT format + add eval-only HF Jobs script

env: meta-RL refactor (continuous profiles, action+belief, adaptation grader)

Add Run 3 training results: plots, training log, README update

docs: fix README accuracy + add training results structure

Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline

Fix bugs, add tests, and improve code quality

Rewrite README for hackathon human review

Initial commit: RhythmEnv daily planning RL environment