---
title: Oracle DAgger
family: oracle-curriculum
summary: Copy the future-reading teacher's moves, then let the copy play and ask the teacher what it should have done in the positions the copy reached.
status: rejected
evidence: task-record only
reads: teacher
---

Copy the moves of a planner that can see the future. Then let the copy play,
and ask the teacher what it *should* have done in every position the copy got
itself into.

<EvidenceLabel status="rejected" evidence="task-record only" reads="teacher" />

## The problem it was built to fix

Plain imitation has a well-known weakness. A student trained only on the
teacher's games sees only the kinds of positions a very strong player reaches.
The first time the student makes a mistake it lands somewhere the teacher never
visited, so its next choice is a guess, which makes things worse, and the errors
compound. The classical fix — collect data *where the student actually goes*,
label it with the teacher, and add it to the pool — is what the acronym DAgger
names, and this approach is that fix applied here.

## What each side was allowed to see

The teacher deliberately reads one training game's **exact future tape**: the
discs to come and the hidden gray numbers. It is the same beam planner as the
[perfect-information oracle](/approaches/oracle-curriculum/perfect-information-oracle),
run here at depth 4 with a beam of 128 by default.

The student receives **no seed, no tape, no move index, no score and no level**.
Its input is a list of canonical position tokens (what is on each cell) plus
the five-move rise phase, the column heights, and the disc it is about to place.
Its output is one of seven columns.

## How it works, step by step

1. Play a set of games with the teacher and record every position, in the
   student's public encoding, labelled with the teacher's column.
2. Train the student on that pool for a first block of epochs, with a little
   label smoothing so it never becomes certain.
3. **Let the student drive.** Play a second set of games in which the student
   chooses the moves, and at every position ask the teacher — who can see that
   game's future, which column it would have played. These are the positions
   plain imitation never covers.
4. Add those labelled positions to the same pool and retrain on the union at
   half the learning rate.
5. Play probe games with the frozen student to see whether it improved.

## What happened

It did not work, and the retained description of why is short: the student
drifted, and the teacher's choices were not recoverable from the public state.

The second half of that sentence is the important one. DAgger is the standard
remedy for the *first* half: a student wandering into unfamiliar positions —
and applying the remedy did not rescue the result, because the obstacle was
never really the distribution of positions. It was that two boards which look
identical to a player can have opposite best moves depending on gray numbers
the player cannot see, and no amount of extra labelled positions makes an
invisible difference visible.

<Callout title="This page has no measured numbers to quote" tone="warn">
This experiment is recorded as **task-record only**. The
[experiment index](/docs/research/experiment-index) carries its status and its
one-line outcome; the [ledger](/docs/research/history) has **no entry** for it,
mentioning the file only as a predecessor of the later native distillation. No
accuracy, score, move count or cohort size is retained anywhere in this
repository, so none is quoted here.
</Callout>

<TechnicalDetails>

- Status of record: **rejected; task-record only**
  ([experiment index](/docs/research/experiment-index), "Oracle and curriculum
  research"): "the student drifted and oracle choices were not recoverable from
  public state."
- Read from the source rather than from a result: teacher depth 4 / beam 128 by
  default, 500-move cap; the student is a small sparse action network with a
  32-wide accumulator and 16 hidden units, trained with label smoothing 0.05,
  Adam and gradient clipping; the default schedule is 15 epochs on the teacher
  pool, then DAgger collection, then 10 epochs on the union at half the learning
  rate; the example pool is capped at 50,000. Training seeds start at
  `0x3d700000`, DAgger seeds at `0x3d710000`, probe seeds at `0x4d700000`.
- [`audit-05`](/docs/exploratory/audit-05-optimistic-curriculum) §4 classifies
  this as failure 2 of 17: primary mode "representation / information gap", with
  distribution shift secondary, and observes that "DAgger exists precisely to fix
  distribution shift; it still failed." §3 of the same audit notes that the
  two-stage schedule here is *data aggregation*, not an ordering experiment —
  the trainer reshuffles the whole pool every epoch, so this run says nothing
  about whether the order of training examples matters.
- The closely related native experiment that *was* measured is
  [oracle distillation](/approaches/oracle-curriculum/oracle-distillation), whose
  held-out top-1 accuracy of 0.218 is the nearest thing to a number for the same
  hypothesis.
- Source: `main.ts`.

</TechnicalDetails>

## What this taught us, and what is still open

- **Distribution shift was not the binding constraint.** That is a real
  conclusion, and it redirected later work away from "collect better positions"
  and towards "stop asking the student to reproduce a privileged choice".
- **A task-record-only result stays task-record only.** It is enough to justify
  not repeating this exact configuration; it is not enough to cite as a measured
  quantity, and the repository does not upgrade it by restating it.
- **Still open:** the same aggregation loop against a teacher whose advantage is
  public rather than privileged. That is the shape of the later
  [planner distillation](/approaches/lifetime-objective/planner-distill) work,
  which had a fair teacher and still failed its held-out sibling-ranking gate —
  for reasons documented in
  [finding-11](/docs/exploratory/finding-11-planner-distillation).