Comments (3)
Exactly, it is related to the window length. Let's assume that your observations have shape (10, 20)
. If window_length=4
, the input to the network would be of shape (4, 10, 20)
. If you use flatten or not depends on what you want to achieve. In the Atari example, the convolution is performed before flattening since the same set of filter should be used for each frame. In other examples, it might make more sense to flatten immediately.
In the case of the cartpole example, the window length is 1 (since the observation already contains velocities etc.). Flattening the input thus simply reduces the dimension by one and otherwise keeps the observation identical.
Does this clarify things?
from keras-rl.
Closing this since the question has (hopefully) been answered. If you this needs further clarification, please re-open the issue.
from keras-rl.
Hello, the question was answered; sorry for not responding due to my tight
work schedule. I should have left some message.
Thanks a lot for the answer.
Yongduek Seo
Professor
+82 10 9296 8896
Department of Media Technology
Sogang University, Korea
On 6 September 2016 at 22:21, Matthias Plappert [email protected]
wrote:
Closed #19 https://github.com/matthiasplappert/keras-rl/issues/19.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
https://github.com/matthiasplappert/keras-rl/issues/19#event-779320444,
or mute the thread
https://github.com/notifications/unsubscribe-auth/AD3huKH15Fc3-hW7tWFlwbmrC39T88Hnks5qnWjygaJpZM4JtAFK
.
from keras-rl.
Related Issues (20)
- Numpy data wrangling in rl/callbacks.py HOT 1
- C:\Python\Python37\lib\site-packages\keras_rl-0.4.2-py3.7.egg\rl\agents\dqn.py in __init__(self, model, policy, test_policy, enable_double_dqn, enable_dueling_network, dueling_type, *args, **kwargs) HOT 4
- [Question] Custom Environment HOT 1
- ValueError: probabilities contain NaN in policy.py HOT 5
- Module 'keras.utils.generic_utils' has no attribute 'populate_dict_with_module_objects' HOT 2
- Undocumented version requirements for python, tensorflow, and keras HOT 3
- Training performance is quite slow HOT 3
- Issue importing keras-rl on tensorflow-macos HOT 4
- ImportError: cannot import name 'PrioritizedMemory' from 'rl.memory' HOT 1
- how to implement a custom environment? HOT 1
- which version the tensorflow and numpy it is inDQN_carpole? HOT 1
- <rl.agents.dqn.DQNAgent object at 0x000001FE98873A88> HOT 1
- How to set the "nb_steps_warmup" and "nb_steps" properly? HOT 1
- Multiple Actions in DQN (binary action vector)
- Value error when running DQN.fit HOT 2
- gym.Env.reset() no longer returns observation of type np.array but a tuple of (observation, info)
- Keras-RL2 DQN agent fails to learn on some environments
- Frame Skipping in DQN
- ValueError: Could not interpret optimizer identifier: <keras.src.optimizers.adam.Adam object at 0x79d9071160e0>
- Recommendation to synchronize tf, keras and keras rl versions? HOT 3
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 keras-rl.