Comments (6)
I also noticed excessive memory usage which didn't happen before.
from tensorflow-deepq.
Yeah, I notice that as well. Maintaining two separate copies of the network is critical for the deep q performance, so I really want to keep it, but I am not sure what causes the leak. I will keep looking. Let me know if you find anything.
One possible thing to investigate is logging. (try passing summary writter=None
from tensorflow-deepq.
Fixed in 0d848e5
from tensorflow-deepq.
Thanks!
So the issue was caused by SummaryWriter and not by having 2 q-networks. That's good to know ) Though, graphs were beautiful ) Do you think it's a TF issue?
from tensorflow-deepq.
Nah, check out the closing commit. The issue was the fact that I create multiple tf.no_op() operations (one every training step). Apparently that's really bad. I was extremely surprised. But I guess there's some logic to it...
from tensorflow-deepq.
Aaah... I saw it, but you set calculate_summaries = False
as well, so I thought that was the main reason. Now I enabled summary and see that it works as fast as before - that's great!
Agree that there could be logic - if you create thousands instances of new nodes, even if they are exact the same, it can very wasteful, if not cached somehow internally in TF.
from tensorflow-deepq.
Related Issues (20)
- Saved Models, tf.train.Saver HOT 4
- How to save/restore saved model HOT 2
- undefined symbol: PyClass_Type HOT 5
- What approach is used to train continuous controller in tensorflow-deepq? HOT 6
- Discrete Hill python notebook HOT 1
- Question about observation list in karpathy_game.py HOT 1
- TF version, circular import dependencies, AttributeError: 'module' object has no attribute 'ops HOT 4
- Links to theory for continuous branch HOT 1
- How long training for this game? HOT 3
- where does the tensorflow model gets saved HOT 1
- i don't understand how to use this HOT 20
- it always stuck at ... HOT 1
- Deep Q Controller Possible Error HOT 2
- DoublePendulum notebook outdated HOT 1
- Add more drawing options HOT 2
- New features to add: PolicyGradient, OpenAI Gym, Keras, Asynchronous Training
- Hi, your work is awesome, but could you provide more tutorial docs that we can learn with your code?
- Need some help... Is it possible to extend it to be a multiagents version?? HOT 1
- Dependency missing HOT 1
- ImportError: No module named 'tf_rl' 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 tensorflow-deepq.