Deep reinforcement learning involves building a deep learning model which enables function approximation between the input features and future discounted rewards values also called Q values. We have seen how we can effectively get these q values and create a map consisting of input features and corresponding set of q values in this article.
This map of input features and all possible q values at a given state enables the Reinforcement learning agent get an overall picture of environment which further helps the agent in choosing the optimal path.
Read the rest of the article at Mindboard’s Medium channel.
About the author