Hands-On Deep Learning with Go

Remember, act, and replay!

Beyond the usual suspects involved in our neural network, we need to define additional functions for our agent's memory. The remember function takes a number of inputs, as follows:

• State
• Action
• Reward
• Next state
• Is done

It appends these values to the memory (that is, a sequentially ordered list).

We now define how an agent takes an action in an act function. This is where we manage the balance between the exploration of the state space and the exploitation of learned knowledge. These are the steps to follow:

1. It takes in one value, that is, the state.
2. From there, it applies epsilon; that is, if a random value between 0 and 1 is less than epsilon, then take a random action. Over time, our epsilon decays, reducing ...