Dongdong Bai's repositories
-
本论文题目为基于深度强化学习的德州扑克AI算法优化
AI-Conference
The most complete list of AI top meetings
AlphaTree-graphic-deep-neural-network
深度神经网络(DNN)与对抗神经网络(GAN)模型总览图示，建立模型发展路书(roadmap),方便大家的理解与学习
caj2pdf
Convert CAJ (China Academic Journals) files to PDF. 转换**知网 CAJ 格式文献为 PDF。佛系转换，成功与否，皆是玄学。
CFRM-ES-CFU-XGBoost
Counterfactual Regret Minimization (External Sampling CFU /w Probing) using XGBoost models for Heads-Up Limit Poker.
chatgpt-web
使用 express 和 vue3 搭建的 ChartGPT 演示网页
duckduckgo-api
免费的无限制的搜索接口
LeducPoker
Python implementation of Deepstack In Leduc Hold'em
LeducTrainingPoisoning
Training Data Poisoning In Imperfect Information Games Implementation
leela-zero
Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.
libratus-impl
On-going project of implementation for Libratus (https://science.sciencemag.org/content/359/6374/418).
nash-finder
Find Nash equilibrium for all games
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
PyDeepLeduc
Python implement of DeepStack-Leduc
PyStack
Python implementation of Deepstack
ReinforcemengLearningPractice
Reinforcement Learning Algorithm Package & PuckWorld, GridWorld Gym environments
rl-book
Source codes for the book "Reinforcement Learning: Theory and Python Implementation"
rlcard
Testbed for Reinforcement Learning / AI Bots in Card (Poker) Games
rlpoker
Reinforcement learning algorithms to play Poker
slumbot2019
Implementations of CFR for solving a variety of Holdem-like poker games
Superhuman_AI_in_multiplayer_poker_-
该论文主要介绍了美国卡内基梅隆大学团队，在多人德州扑克上的人工智能新思路，即不再简单寻找纳什均衡，而引入悔恨值的概念，自我博弈，并采用蒙特卡洛CFR方法，构建蓝图，该方法通用性强，该团队声称他们的德州扑克蓝图只在两枚CPU运算8天即可得出蓝图，即可以实现实时博弈。现已经有国内团队将其用在了斗地主上面，成效显著。
TexasHoldemSolverJava
A Java implemented Texas holdem and short deck Solver
ucasthesis
LaTeX Thesis Template for the University of Chinese Academy of Sciences