OpenAI gym CartPole-v0 using keras with TensorFlow backend

Keras is an open source neural network library written in Python. It is capable of running on top of MXNet, Deeplearning4j, Tensorflow, CNTK or Theano. OpenAI gym is A toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents everything from walking to playing games like Pong or Go.

OpenAI gym

OpenAI gym Environment (https://gym.openai.com/envs)

Prerequisites

1. Python3.2 or higher (https://www.python.org/downloads/)
2. keras (https://keras.io/)
3. tensorflow (https://www.tensorflow.org/install/)

Keras uses the following dependencies:

• numpy, scipy
• yaml
• HDF5 and h5py (optional, required if you use model saving/loading functions) Optional but recommended if you use CNNs: cuDNN.