Building blocks of reinforcement learning

Apart from the interaction between the agent and the environment, there are other factors at play within the RL system:

Figure 1: Components of reinforcement learning

Typically, RL agents perform the following steps:

1. There is a set of states related to the agent and the environment. At a given point of time, the agent observes an input state to sense the environment.
2. There are policies that govern what action needs to be taken. These policies act as decision-making functions. The action is determined based on the input state using these policies.
3. The agent takes the action based on the previous step.
4. The environment reacts in response to that action. The agent receives reinforcement, also known as reward, from the environment.
5. The agent calculates and records the information about this reward. It's important to note that this reward is received for this state/action pair so that it can be used to take...