yhyu13 / Alphagozero Python Tensorflow
Licence: mit
Congratulation to DeepMind! This is a reengineering implementation (on behalf of many other git repo in /support/) of DeepMind's Oct19th publication: [Mastering the Game of Go without Human Knowledge]. The supervised learning approach is more practical for individuals. (This repository has single purpose of education only)
Stars: ✭ 292
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Alphagozero Python Tensorflow
wavenet-classifier
Keras Implementation of Deepmind's WaveNet for Supervised Learning Tasks
Stars: ✭ 54 (-81.51%)
Mutual labels: supervised-learning, deepmind
alpha-zero
AlphaZero implementation for Othello, Connect-Four and Tic-Tac-Toe based on "Mastering the game of Go without human knowledge" and "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm" by DeepMind.
Stars: ✭ 68 (-76.71%)
Mutual labels: deepmind
muzero
A simple implementation of MuZero algorithm for connect4 game
Stars: ✭ 87 (-70.21%)
Mutual labels: deepmind
Kaio-machine-learning-human-face-detection
Machine Learning project a case study focused on the interaction with digital characters, using a character called "Kaio", which, based on the automatic detection of facial expressions and classification of emotions, interacts with humans by classifying emotions and imitating expressions
Stars: ✭ 18 (-93.84%)
Mutual labels: supervised-learning
textlytics
Text processing library for sentiment analysis and related tasks
Stars: ✭ 25 (-91.44%)
Mutual labels: supervised-learning
scan
SCAN: Learning Abstract Hierarchical Compositional Visual Concepts
Stars: ✭ 54 (-81.51%)
Mutual labels: deepmind
Yolov3 Tensorflow
Implement YOLOv3 with TensorFlow
Stars: ✭ 279 (-4.45%)
Mutual labels: supervised-learning
tetrisRL
A Tetris environment to train machine learning agents
Stars: ✭ 44 (-84.93%)
Mutual labels: supervised-learning
Chess-Zero
Chess reinforcement learning by AlphaZero methods.
Stars: ✭ 36 (-87.67%)
Mutual labels: supervised-learning
first-neural-network
Simple neural network implemented from scratch in C++.
Stars: ✭ 17 (-94.18%)
Mutual labels: supervised-learning
machine-learning-course
Machine Learning Course @ Santa Clara University
Stars: ✭ 17 (-94.18%)
Mutual labels: supervised-learning
robo-vln
Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"
Stars: ✭ 34 (-88.36%)
Mutual labels: supervised-learning
reinforce-js
[INACTIVE] A collection of various machine learning solver. The library is an object-oriented approach (baked with Typescript) and tries to deliver simplified interfaces that make using the algorithms pretty simple.
Stars: ✭ 20 (-93.15%)
Mutual labels: deepmind
zoofs
zoofs is a python library for performing feature selection using a variety of nature-inspired wrapper algorithms. The algorithms range from swarm-intelligence to physics-based to Evolutionary. It's easy to use , flexible and powerful tool to reduce your feature size.
Stars: ✭ 142 (-51.37%)
Mutual labels: supervised-learning
relation-network
Tensorflow Implementation of Relation Networks for the bAbI QA Task, detailed in "A Simple Neural Network Module for Relational Reasoning," [https://arxiv.org/abs/1706.01427] by Santoro et. al.
Stars: ✭ 45 (-84.59%)
Mutual labels: deepmind
Edge2Guard
Code for PerCom Workshop paper title 'Edge2Guard: Botnet Attacks Detecting Offline Models for Resource-Constrained IoT Devices'
Stars: ✭ 16 (-94.52%)
Mutual labels: supervised-learning
100 Days Of Ml Code
100-Days-Of-ML-Code中文版
Stars: ✭ 16,797 (+5652.4%)
Mutual labels: supervised-learning
L2c
Learning to Cluster. A deep clustering strategy.
Stars: ✭ 262 (-10.27%)
Mutual labels: supervised-learning
AlphaGOZero (python tensorflow implementation)
This is a trial implementation of DeepMind's Oct19th publication: Mastering the Game of Go without Human Knowledge.
DeepMind release AlphaZero Teaching Go. It's a lot of fun!
From Paper
Pure RL has outperformed supervised learning+RL agent
SL evaluation
Download trained model
-
https://drive.google.com/drive/folders/1Xs8Ly3wjMmXjH2agrz25Zv2e5-yqQKaP?usp=sharing
-
Place under ./savedmodels/large20/
Set up
Install requirement
python 3.6 tensorflow/tensorflow-gpu (version 1.4, version >= 1.5 can't load trained models)
pip install -r requirement.txt
Download Dataset (kgs 4dan)
Under repo's root dir
cd data/download
chmod +x download.sh
./download.sh
Preprocess Data
It is only an example, feel free to assign your local dataset directory
python preprocess.py preprocess ./data/SGFs/kgs-*
Train A Model
python main.py --mode=train
Play Against An A.I.
python main.py --mode=gtp —-gtp_poliy=greedypolicy --model_path='./savedmodels/your_model.ckpt'
Play in Sabaki
- In console:
which python
add result to the headline of main.py with #! prefix.
- Add the path of
main.pyto Sabaki's manage Engine with argument--mode=gtp
TODO:
- [x] AlphaGo Zero Architecture
- [x] Supervised Training
- [x] Self Play pipeline
- [x] Go Text Protocol
- [x] Sabaki Engine enabled
- [ ] Tabula rasa (failed)
- [x] Distributed learning
Credit (orderless):
*Brain Lee *Ritchie Ng *Samuel Graván *森下 健 *yuanfengpang
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].