yotamish / mini-Alpha-Go
A simplified version of DeepMind's AlphaGo for playing Connect4
☆7Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for mini-Alpha-Go
- Connect4 reinforcement learning by AlphaGo Zero methods.☆114Updated 3 years ago
- Unofficial attempt to rebuild AlphaGo Zero☆56Updated 6 months ago
- Congratulation to DeepMind! This is a reengineering implementation (on behalf of many other git repo in /support/) of DeepMind's Oct19th …☆341Updated 2 years ago
- LeelaZero + PhoenixGo's weights☆19Updated 5 years ago
- Sandbox for playing with neural nets for Go☆74Updated 5 years ago
- My implementation of AlphaZero for gomoku (Wu Zi Qi, 五子棋); Poorman's AlphaZero☆10Updated 6 years ago
- Using web browser connect leela zero to analyze game go anywhere☆21Updated 2 years ago
- Go-playing neural network in Python using TensorFlow☆70Updated 8 years ago
- A Policy Network in Tensorflow to classify chess moves☆18Updated 8 years ago
- alphagomoku☆61Updated 7 years ago
- Artificial go player based on reinforcement and supervised learning☆47Updated last year
- Minimalistic AlphaGoZero-like Engine☆274Updated 6 years ago
- OpenAI Gym Env for game Gomoku(Five-In-a-Row, 五子棋, 五目並べ, omok, Gobang,...)☆85Updated last month
- datasets for computer go☆147Updated 5 months ago
- Website for MiniGo, Leela-Zero and other Go data☆20Updated 4 years ago
- A student implementation of Alpha Go Zero☆279Updated 6 years ago
- Computer Go Program. Download//github.com/zakki/Ray/releases☆149Updated last year
- Computer go engine using Monte-Carlo Tree Search (MCTS)☆70Updated last month
- A GTP engine for the game of Go☆8Updated last month
- Leela Master weight is training from leela zero self-play sgf and human sgf file☆51Updated 5 years ago
- 9x9 AlphaGo☆13Updated 8 years ago
- Michi-c2 --- development version for michi-c☆25Updated 2 years ago
- Reversi reinforcement learning by AlphaGo Zero methods.☆677Updated last year
- Auto hybrid and test Leela Zero weights☆16Updated 6 years ago
- Learning from zero (mostly based off of AlphaZero) in General Game Playing.☆82Updated last year
- An asynchronous/parallel method of AlphaGo Zero algorithm with Gomoku☆188Updated 4 years ago
- using CNN to do move prediction and board evaluation for the board game Go☆144Updated 6 years ago
- Go Engine based on Monte-Carlo☆10Updated 8 years ago
- Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.☆9Updated 5 years ago
- Deep Learning big homework of UCAS☆37Updated 5 years ago