TensorFlow Reinforcement Learning Quick Start Guide

Using the model.py file

Let's first code the model.py file. The steps involved in this are as follows:

1. Import the required packages:

import numpy as npimport sysimport osimport randomimport tensorflow as tf

2. Choose the bigger or smaller network: We will use two neural network architectures, one called bigger and the other smaller. Let's use the bigger network for now; the interested user can later change the network to the smaller option and compare performance:

NET = 'bigger' # 'smaller'

3. Choose the loss function (L2 loss or the Huber loss): For the Q-learning loss function, we can use either the L2 loss or the Huber loss. Both options will be used in the code. We will choose huber for now:

LOSS = 'huber' # 'L2'

4. Define neural network ...