---
# edu-lqky
title: 'Write §11: Exercise 3 — train the network on MCTS data'
status: todo
type: task
created_at: 2026-03-13T20:03:17Z
updated_at: 2026-03-13T20:03:17Z
parent: edu-coqp
---

Exercise: generate training examples (state, policy vector, value) from pure MCTS self-play; run one training epoch; log loss.