Comments (4)
I solved it by changing part of your code.
At ActionNetwork.py:
Replace Steering = Dense(.... and following 3 lines Dense call with
Dense(1,activation='tanh',init=lambda shape:VarianceScaling(scale=1e-4)(shape))(h1)
and from keras.initializers import VarianceScaling
then the code works correctly.
from ddpg-keras-torcs.
from ddpg-keras-torcs.
I was facing this keras(2.0.5) and tensorflow (gpu 1.2.1) version mismatch problem too. And I replaced what you did, and it stoped error, but it keeps relauching torcs, I am not sure it is training??
from ddpg-keras-torcs.
Could someone elaborate on what the lines
Steering = Dense(1,activation='tanh',init=lambda shape, name: normal(shape, scale=1e-4, name=name))(h1)
or the replaced
Steering = Dense(1,activation='tanh',init=lambda shape:VarianceScaling(scale=1e-4)(shape))(h1)
exactly do? I understand that it creates a layer outputting one scalar value with the activation function tanh (values -1 to 1) using the input layer h1. However I am confused by the way the lambda command and the shape keyword is used.
I assume it is used to initialize the kernel weights of the output layer to normally distributed values with respect to amount of input and output values? Is there maybe a "more beginner friendly" way to write those lines? Thanks in advance
from ddpg-keras-torcs.
Related Issues (20)
- Episode error HOT 4
- The train problem! HOT 2
- The run errors! HOT 2
- how to use GPU when training
- Text mode is the only way to accelerate the training process? HOT 6
- Thank you for your answer, thank you very much.
- My agent does not learn any reasonable policy At ALL.
- Getting error HOT 1
- Terminal state problem
- ValueError: Output tensors to a Model must be the output of a Keras `Layer` (thus holding past layer metadata). Found: <keras.layers.merge.Concatenate object at 0x7fe49425c5f8>
- ValueError: Shapes (3, ?, 1) and () are incompatible HOT 4
- i have a mistake when i install the torcs, it's confused. HOT 1
- Time required to train HOT 3
- How to run the car for a full lap
- the agent stopped taking any actions while the training still running HOT 1
- I need your help
- The agent has been rebooting!
- Modify the attributes of added vehicles in "quick race".
- The weights provided don't perform well, the car run about just 6 secs and go the wrong way, then it stopped, should i need to trained from scratch?
- The generated image does not contain the information of the entire interface 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 ddpg-keras-torcs.