Simon Shi的小站

人工智能,机器学习 学习记录


  • Home

  • About

  • Tags

  • Categories

  • Archives

Poker Algorithm developer history

Posted on 2019-08-16 | In Game

[toc]

Poker Algorithm developer history

论文阅读《Regret minimization in games and the development of champion multiplayer computer poker playing agents》(游戏中的遗憾最小化与多人计算机扑克游戏冠军的发展)

Read more »

MCTS-CFR

Posted on 2019-08-15 | In AI , Game , RL

[toc]

CFR

类似强化学习的算法

遗憾值(regret) : 在一局石头剪刀布中,对手出了布,玩家出了石头,结果是玩家输了-1。这时的遗憾值为{石头:0,布:1,剪刀:2}。也就意味着如果执行其他动作会比执行当前的动作有多少优势。

遗憾值匹配(regret matching) : 遗憾匹配,通过计算出的遗憾值更新策略。最常用的是将遗憾动作值归一化为生成概率。这种方法可以通过自我对局来最小化预期的regret。

Read more »

MCTS GO

Posted on 2019-08-15 | In AI , Game , RL , Game

[toc]

MCTS_Lee

apply:

  1. GO : UCT (MCTS + UCB)
  2. Pluribus : MCTS-CFR
  3. Dota2 : MCTS
  4. StarCraft2 : MCTS
Read more »

Hello World

Posted on 2019-08-15 | In Hello

Welcome to Hexo! This is your very first post. Check documentation for more info. If you get any problems when using Hexo, you can find the answer in troubleshooting or you can ask me on GitHub.

Read more »

DL_books

Posted on 2019-08-03 | In AI , Book , DeepLearning
Deep Learning Book online 深度学习理论与实战:提高篇 -李理 hexo + latex = blog
Read more »

Template Markdown

Posted on 2019-01-01 | In Tools
12
Read more »
1…2829

Simon Shi

286 posts
132 categories
243 tags
RSS
© 2024 Simon Shi
Powered by Hexo
|
Theme — NexT.Muse v5.1.4