Comments (1)
Hi,
Thanks for being interested in the project. To answer your questions in order:
- We use the Lichess CP scores, which Lichess gets from Stockfish, but they don't run SF on all games so you end up with null entries when we don't have SF evaluations
- CP from Lichess's Stockfish does not have a well defined range: it has both a large range of numerical values and a set of categoricals (e.g. mate in n), plus it is non-linear and non-deterministic. The winrate is an attempt to normalize the CP into a range that's more tractable to deep learning. This is also why we when we run SF we have to do a fixed depth search with no caching
- I've added the mapping to the repo here, we just used a simple lookup table in our work. You could get a more precise mapping by analysing a few months of the Lichess database and running curve fit
- Our models do predict win probability since they also have a value head, thanks to maintaining compatibility with the Leela format. We tested training with the value head loss multiplicative factor (default 1) set low (0.1) and zero during exploration. It didn't change move prediction accuracy noticeably on either condition. I will note that in some of my current work I have found a small improvement if the value head is removed during training, equivalent to the multiplier of 0 condition
Hope this clears things up,
Reid
from maia-chess.
Related Issues (20)
- Could this be used for cheat detection? HOT 4
- Accuracy Elaboration HOT 1
- is possible to tell maia to play a specific gambit to train? HOT 2
- is it possible to train on self-play? HOT 1
- What opening books and tablebases would you suggest? HOT 4
- Unclear instructions/ no instructions for Android HOT 4
- Hello, I am trying to implement maia-chess to my game: HOT 1
- Slow play even with "fast" and one legal move HOT 3
- Move time simulation in python chess HOT 1
- how to use the model HOT 1
- Attempt in recreating the accuracy test results of Maia's paper HOT 1
- Replication on Windows HOT 3
- TypeError: expected str, bytes or os.PathLike object, not list HOT 12
- tfprocess.py doesn't work with Tensorflow=>2.4 HOT 2
- BrokenPipeError: [Errno 32] Broken pipe HOT 9
- what if stretching 'min ply' parameter HOT 1
- Train for maia bellow 1100 HOT 3
- Fast command
- No output when training script is ran HOT 9
- Model Not Implemented Error
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from maia-chess.