deep_learning_and_the_game_of_go
boardgame-research
Our great sponsors
deep_learning_and_the_game_of_go | boardgame-research | |
---|---|---|
3 | 4 | |
929 | 363 | |
- | - | |
0.0 | 3.6 | |
over 1 year ago | 9 months ago | |
Python | XSLT | |
- | Creative Commons Zero v1.0 Universal |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
deep_learning_and_the_game_of_go
-
Training an AI for Tigris and Euphrates
A good book I found is https://www.manning.com/books/deep-learning-and-the-game-of-go
-
Why do engines often evaluate completely winning endgame positions between +60 and +63? What's significant about the low 60's as an evaluation? Or is it just a placeholder when the computer can't quite find a forced mate?
If you want to understand how the new approach used by Leela Zero and Alpha Zero works, the book Deep Learning and the Game of Go is fun and easy to read. Although it's about Go rather than chess, most of the contents are equally relevant to chess.
-
[Q] Deep Learning and the Game of Go - anyone got the code to work?
One of the first hits pointed me to this github repo: https://github.com/maxpumperla/deep_learning_and_the_game_of_go
boardgame-research
- Training an AI for Tigris and Euphrates
-
Board Games and Markov Chains
If you enjoyed this, you might like some of the literature around boardgame research that uses Markov Chains. Prime examples are RISK and Monopoly, but someone wrote a thesis on "Analysis of 'The Settlers of Catan' Using Markov Chains" as well. I maintain a nice list at https://github.com/captn3m0/boardgame-research (grep for Markov)
-
DeepMind's Player of Games, a general-purpose game algorithm
If you are interested in this, I maintain a list of boardgame-solving related research at https://github.com/captn3m0/boardgame-research, with sections for specific games.
This looks really interesting. It would be a good project to test this against a general card-playing framework to easily test it on a variety of imperfect-information games based on playing cards.
-
How to Win at Risk Every Time by Using Systems Thinking
If you're interested in Risk, here's a list of research on Risk: https://github.com/captn3m0/boardgame-research#risk
What are some alternatives?
pyod - A Comprehensive and Scalable Python Library for Outlier Detection (Anomaly Detection)
Sabaki - An elegant Go board and SGF editor for a more civilized age.
deepxde - A library for scientific machine learning and physics-informed learning
mybgg - A template that lets you quickly set up a site for searching and filtering your boardgames.
GeneticAlgorithmPython - Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).
analyze-sgf - Analyze SGF files with KataGo Parallel Analysis Engine to produce Reviewed SGF files.
uncertainty-baselines - High-quality implementations of standard and SOTA methods on a variety of tasks.
Polygames - The project is a platform of zero learning with a library of games.
pycox - Survival analysis with PyTorch
adama-lang - A headless spreadsheet document container service.
Keras - Deep Learning for humans
tigris-and-euphrates - Rust implementation of T&E Board game