Route model learns from bot runs; Thompson sampling in the advisor (work in progress)

- planner/policy.yaml: which sources the route model learns from (spreadsheet,
  reported, bot) and the low-bias sample
- bot runs: deaths coded by stage, Malek intent for runs with a target
- model: survival of the first dragon is not counted when nothing after it is
  known; the meadow dragon falls back to what the bot saw
- solver.js: advisor(..., {sampling: "thompson", seed, draws}) follows one
  posterior draw per attempt and reports each pick's propensity

Not shipped yet: mixing sources lowers the fitted shrinkage for the shadow roll
(alpha 500 -> 50 in the low-bias sample), see the conversation of 2026-11-09.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ
This commit is contained in:
ekcSchiano
2026-11-10 02:29:09 +00:00
co-authored by Claude Opus 5.5
parent d37eaa3378
commit c0355616b6
6 changed files with 121 additions and 22 deletions
+9
View File
@@ -198,6 +198,15 @@ def bot(name, spec):
goal=target if target in COLOURS else None,
outcome=outcome, outcome_color=colour, data_flags="; ".join(flags), **v)
row["attempt_group"] = attempt_group(row["attempt"])
if target: # the bot never bonds a dragon it was not sent for: it dies on purpose instead (Malek)
row["malek_intent"] = "Yes"
if outcome == "Died before the hour" and not o.get("intentional"): # where the game killed it
if row["scream"] == "Unknown":
row["scream"] = "DIED at first sighting"
elif row["scream"] == "Investigate & help" and row["resolution"] == "Unknown":
row["resolution"] = "DIED in combat"
else:
row["hour"] = "DIED before the hour"
# what the bot saw: the shadow at the treetop, and which dragons waited in the meadow
shadow = _seen_after(steps, 0, "shadow")
if row["hour"] == "Tree" and shadow: