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

Reorganize docs: segregate Round 1 and Round 2

Add SPEC.md and hackathon reference docs

Fix bugs, add tests, and improve code quality

Rewrite README for hackathon human review

Add custom task input support and update URLs to HF Space

Initial commit: RhythmEnv daily planning RL environment