chore(edu): archive completed beans and add self-play chapter section tickets [edu-coqp]

Archives completed/scrapped beans from previous chapters (markov, vector
db, compiler). Adds section beans for the self-play ML chapter (edu-coqp).

edu/.beans/edu-3yw9--write-2-monte-carlo-tree-search-algorithm-explaine.md

@@ -0,0 +1,11 @@
+---
+# edu-3yw9
+title: 'Write §2: Monte Carlo Tree Search — algorithm explained'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Step-by-step walkthrough of MCTS: selection (UCB1), expansion, simulation/rollout, backpropagation. Include a worked example on a small game tree.

edu/.beans/edu-453h--write-13-the-full-alphago-zero-training-loop.md

@@ -0,0 +1,11 @@
+---
+# edu-453h
+title: 'Write §13: The full AlphaGo Zero training loop'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Reading lesson: generate → train → evaluate → promote. Discuss the ELO-based model selection step and why it matters.

edu/.beans/edu-4v13--write-8-exercise-2-play-tic-tac-toe-with-pure-mcts.md

@@ -0,0 +1,11 @@
+---
+# edu-4v13
+title: 'Write §8: Exercise 2 — play Tic-Tac-Toe with pure MCTS'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Exercise: wire MCTS to the game logic from Exercise 1 and run a match. Show sample output, discuss iteration count vs strength.

edu/.beans/edu-5go8--write-3-why-self-play-the-alphago-zero-insight.md

@@ -0,0 +1,11 @@
+---
+# edu-5go8
+title: 'Write §3: Why self-play? The AlphaGo Zero insight'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Explain the key insight: a capable engine can be its own teacher. Historical context (AlphaGo vs AlphaGo Zero) and why the approach generalises.

edu/.beans/edu-7lu6--write-12-exercise-4-replace-rollout-with-the-value.md

@@ -0,0 +1,11 @@
+---
+# edu-7lu6
+title: 'Write §12: Exercise 4 — replace rollout with the value network'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Exercise: substitute random rollout in MCTS with a neural-network value estimate; compare strength before and after.

edu/.beans/edu-brtk--write-14-exercise-5-1000-self-play-games-observe-i.md

@@ -0,0 +1,11 @@
+---
+# edu-brtk
+title: 'Write §14: Exercise 5 — 1000 self-play games; observe improvement'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Capstone exercise: run the full self-play loop for 1000 games; plot win-rate over iterations; discuss what worked and what didn't.

edu/.beans/edu-coqp--edu-write-machine-learning-chapter-self-play-game.md

@@ -1,11 +1,11 @@
 ---
 # edu-coqp
 title: 'edu: write Machine Learning chapter (self-play game AI, Alpha Go Zero style)'
-status: todo
-type: task
+status: in-progress
+type: feature
 priority: low
 created_at: 2026-03-10T23:30:01Z
-updated_at: 2026-03-10T23:30:01Z
+updated_at: 2026-03-13T20:03:44Z
 ---
 
 ## Background

edu/.beans/edu-e39n--write-5-representing-game-state-in-rust.md

@@ -0,0 +1,11 @@
+---
+# edu-e39n
+title: 'Write §5: Representing game state in Rust'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Reading lesson: design of Board, Player, Move types. Discuss representation trade-offs (bitboard vs array). Show the full type definitions.

edu/.beans/edu-iv0k--write-9-neural-network-architecture-overview.md

@@ -0,0 +1,11 @@
+---
+# edu-iv0k
+title: 'Write §9: Neural network architecture overview'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Conceptual lesson: shared convolutional trunk, policy head (move probabilities), value head (win probability). Diagrams encouraged. No code yet.

edu/.beans/edu-k3tq--write-4-choosing-a-simple-game-tic-tac-toe.md

@@ -0,0 +1,11 @@
+---
+# edu-k3tq
+title: 'Write §4: Choosing a simple game — Tic-Tac-Toe'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Explain why Tic-Tac-Toe is ideal: small state space, deterministic, zero-sum, easily verifiable. Foreshadow how the same approach scales to Go/Chess.

edu/.beans/edu-lqky--write-11-exercise-3-train-the-network-on-mcts-data.md

@@ -0,0 +1,11 @@
+---
+# 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.

edu/.beans/edu-of9y--write-7-implementing-mcts-in-rust.md

@@ -0,0 +1,11 @@
+---
+# edu-of9y
+title: 'Write §7: Implementing MCTS in Rust'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Walk through selection (UCB1 formula), expansion, simulation (random rollout), backpropagation. Show Rust code for the node structure and the four phases.

edu/.beans/edu-pvou--write-10-integrating-a-neural-network-crate.md

@@ -0,0 +1,11 @@
+---
+# edu-pvou
+title: 'Write §10: Integrating a neural network crate'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Reading lesson: evaluate tch-rs vs candle for this use case; show how to define and initialise the network; basic forward-pass usage.

edu/.beans/edu-wobk--write-1-what-is-reinforcement-learning.md

@@ -0,0 +1,11 @@
+---
+# edu-wobk
+title: 'Write §1: What is reinforcement learning?'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Cover: state, action, reward, policy, value function. Intuitive explanation with a game-playing example. No code.

edu/.beans/edu-ymux--write-6-exercise-1-implement-tic-tac-toe-game-logi.md

@@ -0,0 +1,11 @@
+---
+# edu-ymux
+title: 'Write §6: Exercise 1 — implement Tic-Tac-Toe game logic'
+status: todo
+type: task
+created_at: 2026-03-13T20:03:17Z
+updated_at: 2026-03-13T20:03:17Z
+parent: edu-coqp
+---
+
+Hands-on exercise: move generation, win detection, terminal-state check, displaying the board. Include starter code and expected test output.