[AlphaGo Like Project]MuGo 模仿 AlphaGo 的簡約圍棋引擎

MuGo：模仿 AlphaGo 的簡約圍棋引擎

這是使用 TensorFlow 的純 Python 實現的基於神經網路的圍棋 AI 。

目前，人工智慧僅由一個策略網路組成，有監督訓練學習。 我已經實施了蒙特卡羅樹搜索，但由於用 Python 編寫，模擬太慢了。 我希望通過用一個價值網路替換模擬來完全繞過這個問題，這將需要一個NN評估。 （畢竟，隨機模擬只是對函數的粗略近似，所以如果你有一個很好的價值函數，你將不需要一個實踐...）

這個項目的目標是看看一個純粹基於神經網路的 Go AI有多強大。 換句話說，基於 UCT 的樹搜索與由策略網路驅動的移動，以及用於評估選擇的價值網路。 一個明確的非目標是深入到優化蒙特卡羅模擬的微妙之中。

項目地址：brilee/MuGo

更多機器學習資源：http://www.tensorflownews.com/

MuGo: A minimalist Go engine modeled after AlphaGo

This is a pure Python implementation of a neural-network based Go AI, using TensorFlow.

Currently, the AI consists solely of a policy network, trained using supervised learning. I have implemented Monte Carlo Tree Search, but the simulations are too slow, due to being written in Python. I am hoping to bypass this issue entirely by replacing the simulations with a value network which will take one NN evaluation. (After all, random simulations are but a crude approximation to a value function, so if you have a good enough value function, you wont need a playout...)

The goal of this project is to see how strong a Go AI based purely on neural networks can be. In other words, a UCT-based tree search with moves seeded by a policy network, and a value network to evaluate the choices. An explicit non-goal is diving into the fiddly bits of optimizing Monte Carlo simulations.