RocAlphaGo

An independent, student-led replication of DeepMind's 2016 Nature publication, "Mastering the game of Go with deep neural networks and tree search" (Nature 529, 484-489, 28 Jan 2016), details of which can be found on their website https://deepmind.com/publications.html.

  • 所有者: Rochester-NRT/RocAlphaGo
  • 平台:
  • 許可證: MIT License
  • 分類:
  • 主題:
  • 喜歡:
    2
      比較:

Github星跟蹤圖

RocAlphaGo

(Previously known just as "AlphaGo," renamed to clarify that we are not affiliated with DeepMind)

This project is a student-led replication/reference implementation of DeepMind's 2016 Nature publication, "Mastering the game of Go with deep neural networks and tree search," details of which can be found on their website. This implementation uses Python and Keras - a decision to prioritize code clarity, at least in the early stages.

Build Status
Gitter

Documentation

See the project wiki.

Current project status

This is not yet a full implementation of AlphaGo. Development is being carried out on the develop branch. The current emphasis is on speed optimizations, which are necessary to complete training of the value-network and to create feasible tree-search. See the cython-optimization branch for more.

Selected data (i.e. trained models) are released in our data repository.

This project has primarily focused on the neural network training aspect of DeepMind's AlphaGo. We also have a simple single-threaded implementation of their tree search algorithm, though it is not fast enough to be competitive yet.

See the wiki page on the training pipeline for information on how to run the training commands.

How to contribute

See the 'Contributing' document and join the Gitter chat.

主要指標

概覽
名稱與所有者Rochester-NRT/RocAlphaGo
主編程語言Python
編程語言Python (語言數: 1)
平台
許可證MIT License
所有者活动
創建於2016-02-01 00:40:29
推送於2020-05-05 02:24:57
最后一次提交2016-02-23 19:51:33
發布數0
用户参与
星數9.1k
關注者數0.9k
派生數2.5k
提交數25
已啟用問題?
問題數124
打開的問題數28
拉請求數69
打開的拉請求數2
關閉的拉請求數36
项目设置
已啟用Wiki?
已存檔?
是復刻?
已鎖定?
是鏡像?
是私有?