Core: the route model in Python, built from a declarative game.yaml (#10)

Step 2 of the Python-first, declarative core.

- core/spec/game.yaml: the game as data: every decision and its options, every roll and the
  earlier steps its odds may depend on, every bonding encounter, and the flow of a run from the
  entrance to the dragons (set / keep / drop / go / end / encounter). Also how the form's coded
  answers map onto the game.
- core/atlas/model.py: what each coded run reveals about each step, count tables, empirical-Bayes
  shrinkage, and the posterior draws (same random numbers as before, reproducible from the seed).
- core/atlas/solver.py: one interpreter of game.yaml used three ways (solve, evaluate a fixed
  policy, export the published tree) instead of the tree written out five times. Vectorised
  over the 200 posterior draws: the build takes about 2 minutes instead of 4, with no memory flag.
- planner/build_policy.py and policy_report.py replace the JS build and report.

Checked against the JavaScript model: every number in policy.json agrees to within 4e-12
(last-digit differences in log/cos). Three "still best" shares differ by one draw in 200, at
near-ties under the "eventually" objective. POLICY.md is otherwise identical.
tests/parity/compare_solver.py keeps checking JS against Python in CI until the site's JS advisor
replaces solver.js; tests/core/test_game.py checks game.yaml is complete and consistent.


Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
ekcSchiano
2026-11-03 21:04:21 +00:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 3536007ade
commit cc86343668
19 changed files with 1291 additions and 110 deletions
+74
View File
@@ -0,0 +1,74 @@
"""Build data/public/policy.json: the best decisions for every dragon colour, under both objectives.
python planner/build_policy.py [--draws 200] [--out data/public/policy.json]
Two samples: every run, and a low-bias sample (bulk logs plus form runs from riders not chasing a rare dragon).
The output has a content id, so each bot run can record which policy it followed.
"""
import argparse
import hashlib
import json
import math
import sys
import time
from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT / "core"))
from atlas import coding, model, solver # noqa: E402
def clean(o):
"""JSON-safe: numpy numbers to floats, infinities and NaN to null (as JavaScript's JSON.stringify does)."""
if isinstance(o, dict):
return {str(k): clean(v) for k, v in o.items()}
if isinstance(o, (list, tuple)):
return [clean(v) for v in o]
if hasattr(o, "item"):
o = o.item()
if isinstance(o, float) and (math.isinf(o) or math.isnan(o)):
return None
return o
def coded_runs(path):
df, _ = coding.load(path)
runs = df.drop(columns=["run_id"]).astype(object).where(df.drop(columns=["run_id"]).notna(), None).to_dict("records")
return runs
def main(argv=None):
ap = argparse.ArgumentParser(description=__doc__)
ap.add_argument("--draws", type=int, default=200)
ap.add_argument("--data", default=str(ROOT / "data/public/form_responses.json"))
ap.add_argument("--out", default=str(ROOT / "data/public/policy.json"))
a = ap.parse_args(argv)
rows = len(json.load(open(a.data, encoding="utf-8"))["rows"])
runs = coded_runs(a.data)
samples = {
"all": runs,
"lowBias": [r for r in runs if r["source"] != "Form" or r["goal"] not in model.RARE_GOALS],
}
t0 = time.time()
out = {"schema": 1, "source": {"form_rows": rows}, "samples": {}}
for name, rs in samples.items():
out["samples"][name] = clean(solver.build_policy(rs, draws=a.draws))
print(f"{name}: {len(rs)} runs, {time.time() - t0:.1f} s")
# a content id (no timestamps: the build is reproducible)
out["id"] = hashlib.sha1(json.dumps(out["samples"], separators=(",", ":"), sort_keys=True).encode()).hexdigest()[:12]
Path(a.out).write_text(json.dumps(out, separators=(",", ":")), encoding="utf-8")
print("policy id", out["id"])
pct = lambda p: "–" if p is None else f"{100 * p:.{2 if p < 0.01 else 1}f}%" # noqa: E731
for name, s in out["samples"].items():
print(f"\n{name} alphas {json.dumps(s['model']['alphas'])}")
for X, t in s["targets"].items():
x, e = t["thisAttempt"], t["eventually"]
att = e["expectedAttempts"]["mean"]
print(f" {X:<6} this attempt {pct(x['pX']['mean'])} [{pct(x['pX']['lo'])}, {pct(x['pX']['hi'])}] other bond {pct(x['pOther']['mean'])}"
f" | eventually: ratio {pct(e['ratio']['mean'])}, P(X) {pct(e['pX']['mean'])}, ~{'–' if att is None else round(att)} attempts"
f" | cross-fit {pct(t['crossFit']['inSample'])} -> held-out {pct(t['crossFit']['heldOut'])}")
if __name__ == "__main__":
main()