Comments (2)
I implemented a first MCTS version which can already me used in interactive mode. I thought about implementing this as a model wrapper but the interface doesn't quite match. Maybe we can find a way to merge the two interfaces s.t. MCTS can be used in comparison with models without MCTS without too much extra code.
c_puct
Parameter certainly needs to be tuned. Also currently the prior policy is set to 1
uniformly. Softmax of the move evaluation might make more sense and should certainly be tried.
from hexhex.
I just added a sigmoid(model_output)
factor to U
. Otherwise the first move will be entirely random. Now it looks much better.
from hexhex.
Related Issues (20)
- implement noise in MCTS move selection
- created models require hexconvolution to be in same folder as during creation HOT 1
- saving and loading model and optimizer is too intricate HOT 1
- when all values of the output tensor are 0 there is a division by 0 HOT 1
- model and optimizer shouldn't be saved together HOT 1
- data creation slows down dramatically HOT 1
- current_training_data doesn't allow for parallel training of multiple models HOT 1
- data is in overcomplicated format HOT 6
- validation data is not true validation data HOT 5
- interactive from given starting position HOT 1
- TensorboardX doesn't refresh data HOT 4
- change logic for retrieving position data for gui HOT 1
- create puzzle file automatically for repeated_self_training HOT 2
- creation of the not already existing puzzle data does not work HOT 3
- adapt code for pytorch 1.2 HOT 3
- add Bayesian Optimization for hyperparameter search HOT 3
- introduce learning rate scheduler
- creating elo ratings takes too long for many models HOT 4
- Add coach mode
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 hexhex.