godmoves

DeeperStack

This is an implementation of DeepStack for No Limit Texas Hold'em, extended from DeepStack-Leduc.

Poker_CFR

Counterfactual Regret Minimization for poker games

reinforcement_learning_collections

A collection of deep reinforcement learning algorithm implementations

TexasHoldemBot

DeeperStack: DeepHoldem Evil Brother

HappyGo

A GTP engine for the game of Go

perfectdou

Evaluation of PerfectDou vs DouZero ResNet.

Rock-Paper-Scissors

Regret Matching algorithm for computing Rock-Paper-Scissors Nash Equilibrium

device_management

job_shop

leela-zero

Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.

GoCNN

using CNN to do move prediction and board evaluation for the board game Go

deep_cube

Solving the Rubik’s Cube Without Human Knowledge

bulldog

poker ai

cfr_plus

https://poker.cs.ualberta.ca/cfr_plus.html

CLOP

Confident Local Optimization for Noisy Black-Box Parameter Tuning

DQN_pytorch

FueGo

GitHub clone of SVN repo svn://svn.code.sf.net/p/fuego/code/trunk (cloned by http://svn2github.com/)

GoGui

GoGui is a graphical interface to programs that play the game of Go and use GTP (Go Text Protocol).

GST_FP

lc0

The rewritten engine, originally for tensorflow. Now all other backends have been ported here.

minigo

An open-source implementation of the AlphaGoZero algorithm

mjx

Mjx: A framework for Mahjong AI research

open_cfr

https://poker.cs.ualberta.ca/open_cfr.html

open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

ptan

PyTorch Agent Net: reinforcement learning toolkit for pytorch

rl_cartpole

rok-data

Data for Rise of Kingdoms

rok-talents

Talent builder for Rise of Kingdoms

TCN

Sequence modeling benchmarks and temporal convolutional networks

vim_monokai