Update README.md

asdfjkl · web-flow · commit 2a0c5ea2eb2e · 2021-09-28T10:11:46.000+02:00
diff --git a/README.md b/README.md
@@ -20,14 +20,11 @@ gives a complete introduction into the technical inner workings of such engines.
 
 The book is split into four chapters:
 
-1.) The first chapter introduces neural networks and covers all the basic building blocks that 
+  1.) The first chapter introduces neural networks and covers all the basic building blocks that 
 are used to build deep networks such as those used by AlphaZero. Contents include the perceptron, back-propagation and gradient descent, classification, regression, multilayer perpectron, vectorization techniques, convolutional netowrks, squeeze and exciation networks, fully connected networks, batch normalization and rectified linear units, residual layers, overfitting and underfitting.
-
-2.) The second chapter introduces classical search techniques used for chess engines as well as those used by AlphaZero. Contents include minimax, alpha-beta search, and Monte Carlo tree search.
-
-3.) The third chapter shows how modern chess engines are designed. Aside from the ground-breaking AlphaGo, AlphaGo Zero and AlphaZero we cover Leela Chess Zero, Fat Fritz, Fat Fritz 2 and Effectively Updateable Neural Networks (NNUE) as well as Maia.
-
-4.) The fourth chapter is about implementing a miniaturized AlphaZero. Hexapawn, a minimalistic version of chess, is used as an example for that. Hexapawn is solved by minimax search and training positions for supervised learning are generated. Then as a comparison, an AlphaZero-like training loop is implemented where training is done via self-play combined with reinforcement learning. Finally, AlphaZero-like training and supervised training are compared.
+  2.) The second chapter introduces classical search techniques used for chess engines as well as those used by AlphaZero. Contents include minimax, alpha-beta search, and Monte Carlo tree search.
+  3.) The third chapter shows how modern chess engines are designed. Aside from the ground-breaking AlphaGo, AlphaGo Zero and AlphaZero we cover Leela Chess Zero, Fat Fritz, Fat Fritz 2 and Effectively Updateable Neural Networks (NNUE) as well as Maia.
+  4.) The fourth chapter is about implementing a miniaturized AlphaZero. Hexapawn, a minimalistic version of chess, is used as an example for that. Hexapawn is solved by minimax search and training positions for supervised learning are generated. Then as a comparison, an AlphaZero-like training loop is implemented where training is done via self-play combined with reinforcement learning. Finally, AlphaZero-like training and supervised training are compared.
 
 # About
 
