-
论文地址：https://github.com/borninfreedom/DeepLearning/tree/master/Papers
-
DeepBlue: evaluate positions using features hand-crafted by human grandmasters and carefully tuned weights,combined with a high-performance alpha-beta search that expands a vast search tree using a large number of clever heuristics and domain-specific adaptations.
-
AlphaZero:it replaces the handcrafted knowledge and domain specifc augmentations used in traditional game-playing programs with deep neural networks and tabula rasa reinforcement learning algorithm，using a general purpose Monte-Carlo tree search(MCTS) algorithm.
| AlphaZero | MCTS search |
| Stockfish and Elmo | alpha-beta search |