Commit graph

2 commits

Author SHA1 Message Date
0e5e607c4f Swap inner loop default from CMA-ES to Nelder-Mead (homemaker-py-d6d)
Bakeoff with native fitness shows NM wins at all DOF sizes: +9% at
child_budget=80 for programme-house (6-7 DOF), and decisively at
harbor-house scale (35-40 DOF) where CMA-ES exhausts its convergence
detector after ~3 generations (46 evals) and adds failures on 12/15
runs.  NM uses the full budget, is parameter-free, and has zero new
failures across all test cases.

- Add nm_search() to innerloop.py; change optimise() default to "nm"
- Add nm_search to parametrised test cases
- Add bakeoff_native.py and bakeoff_harbor.py experiments with results

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-14 08:51:22 +01:00
646ee30ab6 Rename package: homemaker → homemaker-layout
- src/homemaker/ → src/homemaker_layout/; all imports updated
- pyproject.toml: name = homemaker-layout, entry point updated
- .beads/config.yaml: dolt sync.remote updated to homemaker-layout.git
- Delete temporary debug/perl scripts from project root
- README.md, DESIGN.md: package path references updated
- GitHub repo renamed; git remote updated

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-14 08:18:06 +01:00
Renamed from src/homemaker/innerloop.py (Browse further)