In this segment, we will implement deep SARSA learning with the keras-rl library. The keras-rl library is a simple neural network API that allows simple and easy implementation of reinforcement learning models (Q, SARSA, and others). To learn more about the keras-rl library, visit the documentation at https://keras-rl.readthedocs.io/en/latest/.
We will be using the same CartPole environment we have been using so far from OpenAI Gym.
A Jupyter Notebook code example for deep SARSA learning can be found at https://github.com/PacktPublishing/Python-Deep-Learning-Projects/blob/master/Chapter14/Deep%20SARSA.ipynb.
