diff --git a/edu/.beans/edu-0w1v--markov-exercise-simulating-a-random-walk-rust.md b/edu/.beans/archive/edu-0w1v--markov-exercise-simulating-a-random-walk-rust.md similarity index 100% rename from edu/.beans/edu-0w1v--markov-exercise-simulating-a-random-walk-rust.md rename to edu/.beans/archive/edu-0w1v--markov-exercise-simulating-a-random-walk-rust.md diff --git a/edu/.beans/edu-16fy--6-recognizing-atoms-integers-booleans-strings-symb.md b/edu/.beans/archive/edu-16fy--6-recognizing-atoms-integers-booleans-strings-symb.md similarity index 100% rename from edu/.beans/edu-16fy--6-recognizing-atoms-integers-booleans-strings-symb.md rename to edu/.beans/archive/edu-16fy--6-recognizing-atoms-integers-booleans-strings-symb.md diff --git a/edu/.beans/edu-18qe--markov-lesson-what-is-a-markov-chain.md b/edu/.beans/archive/edu-18qe--markov-lesson-what-is-a-markov-chain.md similarity index 100% rename from edu/.beans/edu-18qe--markov-lesson-what-is-a-markov-chain.md rename to edu/.beans/archive/edu-18qe--markov-lesson-what-is-a-markov-chain.md diff --git a/edu/.beans/edu-1oh8--12-exercise-5-retrieval-augmented-generation.md b/edu/.beans/archive/edu-1oh8--12-exercise-5-retrieval-augmented-generation.md similarity index 100% rename from edu/.beans/edu-1oh8--12-exercise-5-retrieval-augmented-generation.md rename to edu/.beans/archive/edu-1oh8--12-exercise-5-retrieval-augmented-generation.md diff --git a/edu/.beans/edu-34co--markov-lesson-applications-and-further-reading.md b/edu/.beans/archive/edu-34co--markov-lesson-applications-and-further-reading.md similarity index 100% rename from edu/.beans/edu-34co--markov-lesson-applications-and-further-reading.md rename to edu/.beans/archive/edu-34co--markov-lesson-applications-and-further-reading.md diff --git a/edu/.beans/edu-3sww--11-checking-special-forms.md b/edu/.beans/archive/edu-3sww--11-checking-special-forms.md similarity index 100% rename from edu/.beans/edu-3sww--11-checking-special-forms.md rename to edu/.beans/archive/edu-3sww--11-checking-special-forms.md diff --git a/edu/.beans/edu-4gok--markov-exercise-n-gram-generalization-rust.md b/edu/.beans/archive/edu-4gok--markov-exercise-n-gram-generalization-rust.md similarity index 100% rename from edu/.beans/edu-4gok--markov-exercise-n-gram-generalization-rust.md rename to edu/.beans/archive/edu-4gok--markov-exercise-n-gram-generalization-rust.md diff --git a/edu/.beans/edu-4kkb--12-the-c-runtime-preamble.md b/edu/.beans/archive/edu-4kkb--12-the-c-runtime-preamble.md similarity index 100% rename from edu/.beans/edu-4kkb--12-the-c-runtime-preamble.md rename to edu/.beans/archive/edu-4kkb--12-the-c-runtime-preamble.md diff --git a/edu/.beans/edu-63ze--13-generating-c-atoms-and-expressions.md b/edu/.beans/archive/edu-63ze--13-generating-c-atoms-and-expressions.md similarity index 100% rename from edu/.beans/edu-63ze--13-generating-c-atoms-and-expressions.md rename to edu/.beans/archive/edu-63ze--13-generating-c-atoms-and-expressions.md diff --git a/edu/.beans/edu-6r70--markov-exercise-bigram-text-generator-rust.md b/edu/.beans/archive/edu-6r70--markov-exercise-bigram-text-generator-rust.md similarity index 100% rename from edu/.beans/edu-6r70--markov-exercise-bigram-text-generator-rust.md rename to edu/.beans/archive/edu-6r70--markov-exercise-bigram-text-generator-rust.md diff --git a/edu/.beans/edu-7cp2--markov-exercise-weather-model-rust.md b/edu/.beans/archive/edu-7cp2--markov-exercise-weather-model-rust.md similarity index 100% rename from edu/.beans/edu-7cp2--markov-exercise-weather-model-rust.md rename to edu/.beans/archive/edu-7cp2--markov-exercise-weather-model-rust.md diff --git a/edu/.beans/edu-91j2--vector-db.md b/edu/.beans/archive/edu-91j2--vector-db.md similarity index 100% rename from edu/.beans/edu-91j2--vector-db.md rename to edu/.beans/archive/edu-91j2--vector-db.md diff --git a/edu/.beans/edu-9kuk--markov-lesson-text-generation-with-markov-chains.md b/edu/.beans/archive/edu-9kuk--markov-lesson-text-generation-with-markov-chains.md similarity index 100% rename from edu/.beans/edu-9kuk--markov-lesson-text-generation-with-markov-chains.md rename to edu/.beans/archive/edu-9kuk--markov-lesson-text-generation-with-markov-chains.md diff --git a/edu/.beans/edu-a1al--markov-lesson-transition-probabilities-and-matrice.md b/edu/.beans/archive/edu-a1al--markov-lesson-transition-probabilities-and-matrice.md similarity index 100% rename from edu/.beans/edu-a1al--markov-lesson-transition-probabilities-and-matrice.md rename to edu/.beans/archive/edu-a1al--markov-lesson-transition-probabilities-and-matrice.md diff --git a/edu/.beans/edu-azf5--2-minilisp-language-specification.md b/edu/.beans/archive/edu-azf5--2-minilisp-language-specification.md similarity index 100% rename from edu/.beans/edu-azf5--2-minilisp-language-specification.md rename to edu/.beans/archive/edu-azf5--2-minilisp-language-specification.md diff --git a/edu/.beans/edu-b73b--course-writing-a-lisp-to-c-compiler-in-rust.md b/edu/.beans/archive/edu-b73b--course-writing-a-lisp-to-c-compiler-in-rust.md similarity index 100% rename from edu/.beans/edu-b73b--course-writing-a-lisp-to-c-compiler-in-rust.md rename to edu/.beans/archive/edu-b73b--course-writing-a-lisp-to-c-compiler-in-rust.md diff --git a/edu/.beans/edu-c98s--9-generating-embeddings-in-rust.md b/edu/.beans/archive/edu-c98s--9-generating-embeddings-in-rust.md similarity index 100% rename from edu/.beans/edu-c98s--9-generating-embeddings-in-rust.md rename to edu/.beans/archive/edu-c98s--9-generating-embeddings-in-rust.md diff --git a/edu/.beans/edu-dgfl--11-exercise-4-recommendation-engine.md b/edu/.beans/archive/edu-dgfl--11-exercise-4-recommendation-engine.md similarity index 100% rename from edu/.beans/edu-dgfl--11-exercise-4-recommendation-engine.md rename to edu/.beans/archive/edu-dgfl--11-exercise-4-recommendation-engine.md diff --git a/edu/.beans/edu-g1r5--5-setting-up-the-project.md b/edu/.beans/archive/edu-g1r5--5-setting-up-the-project.md similarity index 100% rename from edu/.beans/edu-g1r5--5-setting-up-the-project.md rename to edu/.beans/archive/edu-g1r5--5-setting-up-the-project.md diff --git a/edu/.beans/edu-ga52--10-exercise-3-semantic-document-search.md b/edu/.beans/archive/edu-ga52--10-exercise-3-semantic-document-search.md similarity index 100% rename from edu/.beans/edu-ga52--10-exercise-3-semantic-document-search.md rename to edu/.beans/archive/edu-ga52--10-exercise-3-semantic-document-search.md diff --git a/edu/.beans/edu-h3yx--10-symbol-tables-and-scope.md b/edu/.beans/archive/edu-h3yx--10-symbol-tables-and-scope.md similarity index 100% rename from edu/.beans/edu-h3yx--10-symbol-tables-and-scope.md rename to edu/.beans/archive/edu-h3yx--10-symbol-tables-and-scope.md diff --git a/edu/.beans/edu-hvic--2-embeddings.md b/edu/.beans/archive/edu-hvic--2-embeddings.md similarity index 100% rename from edu/.beans/edu-hvic--2-embeddings.md rename to edu/.beans/archive/edu-hvic--2-embeddings.md diff --git a/edu/.beans/edu-hvmi--4-what-is-a-vector-database.md b/edu/.beans/archive/edu-hvmi--4-what-is-a-vector-database.md similarity index 100% rename from edu/.beans/edu-hvmi--4-what-is-a-vector-database.md rename to edu/.beans/archive/edu-hvmi--4-what-is-a-vector-database.md diff --git a/edu/.beans/edu-ic66--6-setting-up-turso-sqlite-vec.md b/edu/.beans/archive/edu-ic66--6-setting-up-turso-sqlite-vec.md similarity index 100% rename from edu/.beans/edu-ic66--6-setting-up-turso-sqlite-vec.md rename to edu/.beans/archive/edu-ic66--6-setting-up-turso-sqlite-vec.md diff --git a/edu/.beans/edu-jzvr--4-introduction-to-nom-parser-combinators.md b/edu/.beans/archive/edu-jzvr--4-introduction-to-nom-parser-combinators.md similarity index 100% rename from edu/.beans/edu-jzvr--4-introduction-to-nom-parser-combinators.md rename to edu/.beans/archive/edu-jzvr--4-introduction-to-nom-parser-combinators.md diff --git a/edu/.beans/edu-mlut--1-what-is-a-vector.md b/edu/.beans/archive/edu-mlut--1-what-is-a-vector.md similarity index 100% rename from edu/.beans/edu-mlut--1-what-is-a-vector.md rename to edu/.beans/archive/edu-mlut--1-what-is-a-vector.md diff --git a/edu/.beans/edu-mmbr--8-parsing-atoms-with-nom.md b/edu/.beans/archive/edu-mmbr--8-parsing-atoms-with-nom.md similarity index 100% rename from edu/.beans/edu-mmbr--8-parsing-atoms-with-nom.md rename to edu/.beans/archive/edu-mmbr--8-parsing-atoms-with-nom.md diff --git a/edu/.beans/edu-n7zb--7-the-abstract-syntax-tree.md b/edu/.beans/archive/edu-n7zb--7-the-abstract-syntax-tree.md similarity index 100% rename from edu/.beans/edu-n7zb--7-the-abstract-syntax-tree.md rename to edu/.beans/archive/edu-n7zb--7-the-abstract-syntax-tree.md diff --git a/edu/.beans/edu-n9ap--3-compiler-architecture-the-pipeline.md b/edu/.beans/archive/edu-n9ap--3-compiler-architecture-the-pipeline.md similarity index 100% rename from edu/.beans/edu-n9ap--3-compiler-architecture-the-pipeline.md rename to edu/.beans/archive/edu-n9ap--3-compiler-architecture-the-pipeline.md diff --git a/edu/.beans/edu-nc61--16-the-compilation-pipeline.md b/edu/.beans/archive/edu-nc61--16-the-compilation-pipeline.md similarity index 100% rename from edu/.beans/edu-nc61--16-the-compilation-pipeline.md rename to edu/.beans/archive/edu-nc61--16-the-compilation-pipeline.md diff --git a/edu/.beans/edu-paqf--8-exercise-2-k-nearest-neighbor-search.md b/edu/.beans/archive/edu-paqf--8-exercise-2-k-nearest-neighbor-search.md similarity index 100% rename from edu/.beans/edu-paqf--8-exercise-2-k-nearest-neighbor-search.md rename to edu/.beans/archive/edu-paqf--8-exercise-2-k-nearest-neighbor-search.md diff --git a/edu/.beans/edu-pdeo--7-exercise-1-storing-and-retrieving-vectors.md b/edu/.beans/archive/edu-pdeo--7-exercise-1-storing-and-retrieving-vectors.md similarity index 100% rename from edu/.beans/edu-pdeo--7-exercise-1-storing-and-retrieving-vectors.md rename to edu/.beans/archive/edu-pdeo--7-exercise-1-storing-and-retrieving-vectors.md diff --git a/edu/.beans/edu-pyue--14-generating-c-definitions-and-functions.md b/edu/.beans/archive/edu-pyue--14-generating-c-definitions-and-functions.md similarity index 100% rename from edu/.beans/edu-pyue--14-generating-c-definitions-and-functions.md rename to edu/.beans/archive/edu-pyue--14-generating-c-definitions-and-functions.md diff --git a/edu/.beans/edu-svom--markov.md b/edu/.beans/archive/edu-svom--markov.md similarity index 100% rename from edu/.beans/edu-svom--markov.md rename to edu/.beans/archive/edu-svom--markov.md diff --git a/edu/.beans/edu-twtl--3-vector-similarity.md b/edu/.beans/archive/edu-twtl--3-vector-similarity.md similarity index 100% rename from edu/.beans/edu-twtl--3-vector-similarity.md rename to edu/.beans/archive/edu-twtl--3-vector-similarity.md diff --git a/edu/.beans/edu-tx54--deploy-edu-mdbook-to-cloudflare-pages-at-vibebooks.md b/edu/.beans/archive/edu-tx54--deploy-edu-mdbook-to-cloudflare-pages-at-vibebooks.md similarity index 100% rename from edu/.beans/edu-tx54--deploy-edu-mdbook-to-cloudflare-pages-at-vibebooks.md rename to edu/.beans/archive/edu-tx54--deploy-edu-mdbook-to-cloudflare-pages-at-vibebooks.md diff --git a/edu/.beans/edu-tzzh--9-parsing-s-expressions-and-special-forms.md b/edu/.beans/archive/edu-tzzh--9-parsing-s-expressions-and-special-forms.md similarity index 100% rename from edu/.beans/edu-tzzh--9-parsing-s-expressions-and-special-forms.md rename to edu/.beans/archive/edu-tzzh--9-parsing-s-expressions-and-special-forms.md diff --git a/edu/.beans/edu-unus--15-generating-c-control-flow-and-sequencing.md b/edu/.beans/archive/edu-unus--15-generating-c-control-flow-and-sequencing.md similarity index 100% rename from edu/.beans/edu-unus--15-generating-c-control-flow-and-sequencing.md rename to edu/.beans/archive/edu-unus--15-generating-c-control-flow-and-sequencing.md diff --git a/edu/.beans/edu-urpp--markov-lesson-stationary-distributions.md b/edu/.beans/archive/edu-urpp--markov-lesson-stationary-distributions.md similarity index 100% rename from edu/.beans/edu-urpp--markov-lesson-stationary-distributions.md rename to edu/.beans/archive/edu-urpp--markov-lesson-stationary-distributions.md diff --git a/edu/.beans/edu-uz3e--5-under-the-hood-ann-algorithms.md b/edu/.beans/archive/edu-uz3e--5-under-the-hood-ann-algorithms.md similarity index 100% rename from edu/.beans/edu-uz3e--5-under-the-hood-ann-algorithms.md rename to edu/.beans/archive/edu-uz3e--5-under-the-hood-ann-algorithms.md diff --git a/edu/.beans/edu-v0ud--17-testing-the-compiler.md b/edu/.beans/archive/edu-v0ud--17-testing-the-compiler.md similarity index 100% rename from edu/.beans/edu-v0ud--17-testing-the-compiler.md rename to edu/.beans/archive/edu-v0ud--17-testing-the-compiler.md diff --git a/edu/.beans/edu-y4e6--18-whats-next-extensions-and-further-reading.md b/edu/.beans/archive/edu-y4e6--18-whats-next-extensions-and-further-reading.md similarity index 100% rename from edu/.beans/edu-y4e6--18-whats-next-extensions-and-further-reading.md rename to edu/.beans/archive/edu-y4e6--18-whats-next-extensions-and-further-reading.md diff --git a/edu/.beans/edu-ylb8--1-introduction-what-were-building.md b/edu/.beans/archive/edu-ylb8--1-introduction-what-were-building.md similarity index 100% rename from edu/.beans/edu-ylb8--1-introduction-what-were-building.md rename to edu/.beans/archive/edu-ylb8--1-introduction-what-were-building.md diff --git a/edu/.beans/edu-zjy1--markov-lesson-states-and-transitions.md b/edu/.beans/archive/edu-zjy1--markov-lesson-states-and-transitions.md similarity index 100% rename from edu/.beans/edu-zjy1--markov-lesson-states-and-transitions.md rename to edu/.beans/archive/edu-zjy1--markov-lesson-states-and-transitions.md diff --git a/edu/.beans/edu-3yw9--write-2-monte-carlo-tree-search-algorithm-explaine.md b/edu/.beans/edu-3yw9--write-2-monte-carlo-tree-search-algorithm-explaine.md new file mode 100644 index 0000000..66a8261 --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-453h--write-13-the-full-alphago-zero-training-loop.md b/edu/.beans/edu-453h--write-13-the-full-alphago-zero-training-loop.md new file mode 100644 index 0000000..3323726 --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-4v13--write-8-exercise-2-play-tic-tac-toe-with-pure-mcts.md b/edu/.beans/edu-4v13--write-8-exercise-2-play-tic-tac-toe-with-pure-mcts.md new file mode 100644 index 0000000..a3b9381 --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-5go8--write-3-why-self-play-the-alphago-zero-insight.md b/edu/.beans/edu-5go8--write-3-why-self-play-the-alphago-zero-insight.md new file mode 100644 index 0000000..5cd840f --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-7lu6--write-12-exercise-4-replace-rollout-with-the-value.md b/edu/.beans/edu-7lu6--write-12-exercise-4-replace-rollout-with-the-value.md new file mode 100644 index 0000000..0e3f4ad --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-brtk--write-14-exercise-5-1000-self-play-games-observe-i.md b/edu/.beans/edu-brtk--write-14-exercise-5-1000-self-play-games-observe-i.md new file mode 100644 index 0000000..bb3abb5 --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-coqp--edu-write-machine-learning-chapter-self-play-game.md b/edu/.beans/edu-coqp--edu-write-machine-learning-chapter-self-play-game.md index 3428708..ad8ae64 100644 --- a/edu/.beans/edu-coqp--edu-write-machine-learning-chapter-self-play-game.md +++ b/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 diff --git a/edu/.beans/edu-e39n--write-5-representing-game-state-in-rust.md b/edu/.beans/edu-e39n--write-5-representing-game-state-in-rust.md new file mode 100644 index 0000000..23d48ba --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-iv0k--write-9-neural-network-architecture-overview.md b/edu/.beans/edu-iv0k--write-9-neural-network-architecture-overview.md new file mode 100644 index 0000000..945ebe3 --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-k3tq--write-4-choosing-a-simple-game-tic-tac-toe.md b/edu/.beans/edu-k3tq--write-4-choosing-a-simple-game-tic-tac-toe.md new file mode 100644 index 0000000..f03297b --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-lqky--write-11-exercise-3-train-the-network-on-mcts-data.md b/edu/.beans/edu-lqky--write-11-exercise-3-train-the-network-on-mcts-data.md new file mode 100644 index 0000000..58da37c --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-of9y--write-7-implementing-mcts-in-rust.md b/edu/.beans/edu-of9y--write-7-implementing-mcts-in-rust.md new file mode 100644 index 0000000..87a3431 --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-pvou--write-10-integrating-a-neural-network-crate.md b/edu/.beans/edu-pvou--write-10-integrating-a-neural-network-crate.md new file mode 100644 index 0000000..b876ff0 --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-wobk--write-1-what-is-reinforcement-learning.md b/edu/.beans/edu-wobk--write-1-what-is-reinforcement-learning.md new file mode 100644 index 0000000..762c652 --- /dev/null +++ b/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. diff --git a/edu/.beans/edu-ymux--write-6-exercise-1-implement-tic-tac-toe-game-logi.md b/edu/.beans/edu-ymux--write-6-exercise-1-implement-tic-tac-toe-game-logi.md new file mode 100644 index 0000000..9a7c32c --- /dev/null +++ b/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.