Comments (6)
@amj I have a question for random symmetries on both training and selfplay as current mlperf reference implementation. If random symmetries is added to training, is it really necessary to have random symmetries in MCTS inference as well? I want to understand whether its totally duplication or there are still some subtle difference between do it at training and do it at MCTS selfplay or do both.
from minigo.
The weights in the network aren't symmetric and contain some biases. Apply random symmetries to self play introduces extra diversity to the games and also mitigates the biases inherent in the network.
To give a clear example: if you disabled random symmetries for the evaluation games every single evaluation game would play the exact same game.
from minigo.
What does random symmetry in training serves?Double random seems equal to single random at the first glance.
from minigo.
Random symmetry during training helps prevent the model from overfitting on the selfplay games.
Each 19x19 game will generate about 200 training examples, and every example a game will look very similar to many other examples from the same game. Because the symmetries are applied randomly to the examples, it stops positions from the same game looking similar to each other.
from minigo.
@delock we scratched our heads about this one as well. Originally, we only had random symmetries in selfplay but not in training. Despite this, the networks without symmetries in training were substantially weaker; v7 and earlier did not have symmetries on in training, and they are far weaker than the later versions.
As for the necessity of having them on in selfplay: the MCTS algorithm benefits strongly from having a large set of inferences to average, because any individual inference is very 'noisy'. Having rotations off during selfplay would almost certainly result in weaker play.
I know it seems redundant, i certainly thought so too! But it appears important to have rotation turned on in both places.
from minigo.
Thanks for the explanation @tommadams @amj
from minigo.
Related Issues (20)
- run concurrent selfplay without bazel HOT 1
- Running minigo with Sabaki GUI HOT 2
- Problem while building tpu-image HOT 3
- Problem in features.stone_features HOT 1
- Onscreen buttons in lw_demo don't toggle (work)
- Minigo not working on Coral accelerator HOT 4
- Add Edge TPU support to C++ engine HOT 1
- Decouple the conv data format from the input feature layout HOT 8
- How strong is the model in kyu/dan? HOT 7
- 000990-cormorant: stderr thread died HOT 1
- Wrong argument passed in minigui/fetch-and-run.sh HOT 1
- How to communicate with engine easily outside stdin HOT 2
- Support for sending board state to the engine via GTP HOT 6
- Looking for 9x9 model files in .minigo file format HOT 7
- Error on Minigo v15(990)
- tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: Assign requires shapes of both tensors to match HOT 3
- The setting of num_readouts to get strongest of minigo
- train.sh in cloud tpu
- Minigo training using Coral Dev Board HOT 1
- ./cc/configure_tensorflow.sh 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 minigo.