Oracles, teachers and distillation

The technique

Let a program that can see hidden information make labels, then train a program that cannot see it to copy the labels, and only ever measure the copy.

Read the primer

Approaches using this technique

9 approaches, featured pages first. Each card is one theory of how to choose a column and what happened when it was tried.

Oracles, teachers and distillationfeatured

Compressing a legal planner into a network

Labels every legal move with an expensive public-information planner, then trains a small network to imitate it.

rejectedreproduced

Oracles, teachers and distillationfeatured

Oracle distillation

Show a network thousands of positions labelled with the column a future-reading planner chose, and see whether it can guess that column from the screen alone.

rejectedrecorded

Oracles, teachers and distillation

Board topology

Ask whether a player can recognise, from board shape alone, the positions a future-reading planner creates.

rejectedrecorded

Oracles, teachers and distillation

D4 root-Q clone

Train a tiny fast network to copy how the expensive depth-4 search orders the seven columns.

rejectedrecorded

Oracles, teachers and distillation

Depth-4 distillation

Tests whether a small model can imitate the reference and finds that a cheap exact search does better.

rejectedrecorded

Oracles, teachers and distillation

Expert iteration from the depth-4 search

Learn from the strongest search, play with the result, and repeat. After eight rounds, the learned policy was still less than half as good as its teacher.

rejectedrecorded