Comments (4)
I think the bad solution you mentioned is actually a good solution.
Because the models are trained with lots of varying pot sizes, it can handle any stack size between 1bb and 200bb. If you scale the pot and stack so that stack = 20000 chips, then you can input the situation into the model, as you said.
I don't know how deepstack did it, but I think they will use this method too.
from deepholdem.
Ah that's great. Thank you, that makes a lot of sense. I agree with you, deepstack said they did not retrain their models. So there really is not another way of doing it other than the way you described.
@happypepper This is a bit offtopic but I am really interested what projects you are currently working on. Obviously you dont have to say if you dont want to. Id also be interested in your plans for future poker projects. I personally think 6 man / 9 man poker would be really challenging and interesting.
from deepholdem.
@PhDtimothy and @happypepper I was wondering how exactly one would implement this in code. I have changed the code so I can simply input the current matchstate as a string into deepstack.lua and it outputs its action. But I am not exactly sure how I can change the blind size properly after a hand. Would it be enough to change the arguments.bb and arguments.sb size after a hand is played, so that deepstack.lua solves for the new blind sizes? Thank you many times for your help.
from deepholdem.
Hey @Jedrickbender , did you be able to resolve it? I want to test dynamically different stacks and I'm having issues
from deepholdem.
Related Issues (20)
- Unnecessary init checks?
- Warm-up opponent ranges HOT 3
- can i have your model files? HOT 21
- bucket_conversion invalid arguments while running raw_converter.lua HOT 2
- Bug in terminal_equity.set_call_matrix HOT 3
- bad argument #2 to '?'
- Be the Dealer HOT 2
- arguments.lua - Change SB / BB
- Invalid index in scatterAdd at .../HTensorMath.c:495
- "Not our Turn" with protocol demo data HOT 2
- Assertion "indexValue >=0" failed in next_round_value_pre.lua:114 HOT 2
- Setup environment
- main_train does nothing HOT 1
- Multi agents or change the blind structure HOT 1
- main_train does still nothing HOT 4
- Not playing best strategy?
- Have anyone created a docker file?
- Using Lua and tricky torch makes the project quite unfriendly to newbees HOT 1
- What is to be expected from this project? HOT 2
- Deepholdem.lua Segmentation fault HOT 1
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 deepholdem.