Machine Learning: What is Reinforcement Learning

Reinforcement Learning is an area of Machine Learning which is applied when you don’t have training dataset and want the machine to learn from its experience.

How Reinforcement Learning works:

Step1: A problem is given to the Computer or Agent.

Step 2: The Agent uses trial and error method to find a solution for the given problem.

Step 3: The Agent gets either rewards or penalties from the environment for the actions it performs.

Step 4: The Agent learns from the reward and tries again to find the solution of the problem.

Step 5: Step 2 to Step 4 goes on for several loops or iterations.

Step 6: Agent’s goal is to maximize the total reward.

Main points in Reinforcement Learning:

Input: The input should be an initial state from which the model will start.

Output: There are many possible outputs as there are variety of solution to a particular problem.

Training: The training is based upon the input. The model will return a state and the user will decide to reward or punish the model based on its output.

The Model continues to learn.

The best Solution is decided based on the Maximum Reward.

Difference between Supervised and Reinforcement learning:

Supervised learning uses correct set of output as feedback for performing a task whereas Reinforcement learning uses rewards and punishment as feedback for the actions performed to find the solution.

Difference between Unsupervised and Reinforcement learning:

The goal in Unsupervised learning is to find similarities and differences between data points whereas the goal in Reinforcement learning is to find a suitable action model that would maximize the total cumulative reward of the agent.

Applications of Reinforcement Learning:

Reinforcement Learning is and cab be widely used in the following sectors:

• Gaming
• Robotics
• Industrial Operations
• Supply Chain & Logistics
• Traffic Control
• Bidding & Advertising
• Augmented Natural Language Processing (NLP)

Thank you for reading this blog and happy learning.

Ready to elevate your skills? Click here for my Python book and here for my Machine Learning book on Kindle.