Comments (8)
Maybe. If you could find a way to reliably categorize the styles of different players across tens of thousands of games, then you could add some parameters to the human sgf metadata encoder to label the style and train it. But to start off, you would have to find a way to categorize styles for the games without having a model trained to do it, because you wouldn't have a model yet.
from katago.
define "human-like"
from katago.
@lightvector Thank you for your answer. We are trying to move in this direction.
Another question is, can we use your b18c384nbt-humanv0.bin.gz model and fine-tune it with some specific human game data? This would be to adapt it to specific player styles or differences in rating definitions across various regions.
from katago.
It would also be great to make smaller models, for example b10 human style
from katago.
@jopdorp Good idea~ so which part of the documentation can I refer to in order to implement the training process?🙏
from katago.
@BigBoxxx I think thre are two general approaches here, that is to train a new supervised model from scratch, similar to how @lightvector trained the 18b humansl model, or :
You could take the 18b human sl model, input randomly generated data into it, and the 10b model to be trained, then update the parameters of the 10b model to get closer to the same outputs as the 18b model, this way you would not need any data, and you can get closer to the capabilities of the 18b model.
As a side note, this second approach could also be applied to make more powerful 10b and 20b normal models (non humansl)
from katago.
@jopdorp Thanks jopdorp, what documents can I refer to for training a new supervised model from scratch, similar to the 18b humansl model?
from katago.
@BigBoxxx I think there is just the source code in the python directory
from katago.
Related Issues (20)
- Throwback HOT 4
- Lack of ability HOT 3
- Katago cannot give a definitive answer for the best move. HOT 2
- Report an error HOT 3
- allowResignation affects humanSL strength?? HOT 4
- Loose ladder
- katago 1.15.1 build failure HOT 1
- Do you have a plan to create a GUI? HOT 4
- kata-analyze reports a non-human-like move for the preaz_20k human profile HOT 1
- Evaluate the value of moves HOT 2
- KataGo works with old libssl versions only HOT 5
- katago-v1.15.3-opencl-windows-x64 Server returned error 400: This version of KataGo is not enabled for distributed. HOT 2
- trt 15.3 causes system crashes
- The Homebrew version is still 1.14.1 HOT 20
- What are the difference between ancient-territory and stone-scoring rules? HOT 3
- Effect of pass moves on ownership
- Identify equivalent states in MCTS
- OpenCL tuning fails on Pixel7a MaliG710 GPU
- KataGo v1.15.3 human model failed to start on OGS HOT 2
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 katago.