How to adapt to machine thinking and become an adaptive thinker
Reinforcement learning, one of the foundations of machine learning, supposes learning through trial and error by interacting with an environment. This sounds familiar, doesn't it? That is what we humans do all our lives—in pain! Try things, evaluate, and then continue; or try something else.
In real life, you are the agent of your thought process. In reinforcement learning, the agent is the function calculating randomly through this trial-and-error process. This thought process function in machine learning is the MDP agent. This form of empirical learning is sometimes called Q-learning.
Mastering the theory and implementation of an MDP through a three-step method is a prerequisite.
This chapter will detail the three-step approach that will turn you into an AI expert, in general terms:
- Starting by describing a problem to solve with real-life cases
- Then, building a mathematical model that considers real-life limitations
- Then, writing source code or using a cloud platform solution
This is a way for you to approach any project with an adaptive attitude from the outset. This shows that a human will always be at the center of AI by explaining how we can build the inputs, run an algorithm, and use the results of our code. Let's consider this three-step process and put it into action.
