Comments (5)
I think there's randomness in tensorflow action sampling too. As a result, each round of training will get different action trajectory, and model will go down different path. Try fixing a random seed for that too and see if results are repeatable.
One other potential problem I remember is some numerical instability of tensorflow. The training has multiple agents collecting experience in different processes. Mathematically, the order of getting the experiences to compute the gradient shouldn't matter. But empirically it seems that tensorflow gets different gradient when assembling the experiences in different order. You might also want to keep this in mind if you want repeatable outcome at every run. Hope these help!
from decima-sim.
Thanks for your reply!
And since the algorithm picked up different DAG each episode, how can we tell if Decima has already converged?
from decima-sim.
Looking at reward and entropy signal. You can set a criteria (e.g., signal flat out, or stay within x standard deviation computed from past n signal data point) for training convergence. This part is similar to standard RL training.
from decima-sim.
Thank you very much and sorry to bother you again, I trained with --num_init_dags 5 --num_stream_dags 10, and after several thousand episodes I find the output of policy network is so large that valid_mask can't work at all,which leads to take illegal actions. Could you please tell me is it normal and any possible reasons why could this happen? Thanks!
from decima-sim.
hmmm I don't recall valid_mask
failed. If the policy network can output something, valid_mask
is in the same shape. I don't quite get what you meant by "policy network is so large"? Are the numeric values being too large? That might leads to NaN when very large (basically being treated as Inf) number multiplies 0 at valid_mask
. In another context I have seen behavior like this, it's usually because the agent selects an invalid action in the previous step. Because it was masked with 0, the gradient descent will have an Inf for some parameters, then things blow up. But I don't recall seeing this in this training code.
Here's a pre-trained model #12 You might want to try the same parameters and compare with the model?
from decima-sim.
Related Issues (20)
- some questions of your code HOT 9
- The model training issue with reward function optimizing makespan HOT 14
- Updating Tensorflow 1.14 to 2 HOT 3
- About nodes information HOT 1
- some question about the main idea
- Some questions about Decima's GNN HOT 2
- A question about actor_network HOT 2
- Questions about the input vector HOT 2
- What are the versions of the project pkg requirement? HOT 6
- Question about multi resource training. HOT 1
- when calculating the reward whether the locality of the data to the core is taken into account? in other word,the data transfer between different nodes may significant affect the reward calculation.
- How to integrate Decima in Spark
- About the model of generation HOT 1
- Question about .npy files
- Some questions about executor
- Code for Learning State Representation
- Could u plz tell me the piplist of this code? HOT 2
- Bug in determining `done` in `env.step`?
- PyTorch Implementation of Decima Available!
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 decima-sim.