Comments (2)
werner-duvaud
commented on May 19, 2024
Hi,
Running MuZero on connect4 requires a lot of computing power that we don't have yet. The default hyperparameters may not allow good learning.
We quickly tested it today (slightly increased the number of blocks and the size of the replay buffer), it seems to learn slowly.
What do you call the reward value?
How many self played games do you have for 250k training steps ?
from muzero-general.
fidel-schaposnik
commented on May 19, 2024
If you haven't done so already, you may want to check https://medium.com/oracledevs/lessons-from-alpha-zero-part-6-hyperparameter-tuning-b1cfcbe4ca9a and previous articles in that series to get an idea for the various hyperparameter values you may use (many directly translate from AlphaZero)
from muzero-general.
Related Issues (20)
- Question: Does muzero-general support 2 player games with simultaneous action selection? HOT 3
- TypeError: can't pickle function objects
- Only One Player: Can we use MuZero? HOT 2
- The model does not converge for breakout HOT 11
- Question about the perspective transformation of two players when calculating Q?
- Can't train using GPU? The torch version for this environment is '1.10.0cpu', that is, CPU one. HOT 2
- Question about the dimension of value and reward network
- Mean_value plot in Total_reward - Interpretation
- Without Selfplay, why 1 games on a running?? HOT 2
- Update gym package to gymnasium HOT 1
- Dirichlet noise added outside of training
- The difference between offical pseudo code and this repository about "num_unroll_steps"
- question about action encoded
- Breakout: ModuleNotFoundError shows gym[atari] instead of python-opencv HOT 1
- Muzero crashes when choosing spiel/backgammon
- MuZero choose the same action
- How can I use a pre-trained model? HOT 1
- What does the `replay_buffer.pkl` do? HOT 1
- cross play between models
- Chess and other non-trivial games 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 muzero-general.