Geek Answers Handbook

Python Neural Network Strengthening

I want to create a neural network that learns using reinforcement learning in python.

X -> [ANN] -> yEstimate -> score! -> (repeat until weights are optimised)

I am using Scikit-learn at the moment, but it seems that all things of neural networks are not suitable for yEstimate before yTarget .

Are there scikit-learn secrets or are there other libraries that I don't know about for this?

Thanks!

+7
python scikit-learn reinforcement-learning machine-learning
source share
2 answers

Google TensorFlow is one large Python library for creating neural networks. See https://github.com/nivwusquorum/tensorflow-deepq for details.

+4
source share

Here you have an example http://pybrain.org/

Here's more https://pypi.python.org/pypi/Reinforcement-Learning-Toolkit/1.0

There are many research groups in robotics using amplification training. If you don’t like the ones I gave you, you can try looking in these groups.

+3
source share

More articles:


All Articles