Aswe saw in the above image, we can see the robot is thinking. This is actually Reinforcement Learning, i.e. making computers to learn itself by making various decisions. Let’s look at the definition part:

Reinforcement learning (RL) is an area of machine learning concerned with how software agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning.

Actually, you might find this definition difficulty to understand but don’t worry, even I don’t understand definitions properly. So, let me conclude the definition: Reinforcement Learning is a type of Machine Learning. This learning makes the computer itself to learn from it’s environment, gets reward on successfully completing a task and main aim is to maximize the reward after the end of all tasks. Trough various blogs, I have already completed all supervised and unsupervised Machine Learning algorithms with math intuition, and now it’s time to learn reinforcement learning.

Reinforcement Learning has** great scope** in future, it is said to be the hope of true artificial intelligence. Reinforcement Learning is growing rapidly, producing wide variety of learning algorithms for different applications. Hence it is important to be familiar with the techniques of reinforcement learning.

Terms in Reinforcement Learning

  1. Agent. The program you train to perform specific task is an agent.
  2. **Environment. **The surrounding (real or virtual) in which the agent performs actions.
  3. Action. A move made by the agent, which causes a status change in the environment.
  4. **Rewards. **The evaluation or score of an action performed by agent, which can be positive or negative.

We can understand this terminology by looking at a reinforced learned robot, it will surely be interesting.

Image for post

Source: here

This is basically a plastic cleaning robot, it’s main aim is to collect plastics garbage from the floor. The robot works this way:

  • Gets +10 points when it successfully pick a plastic.
  • Gets** -10** when it hits a person.
  • Gets -50 when it falls off.
  • Gets +50 when it successfully collect all the garbage in desired time.

Here our **Robot is Agent, room’s Floor is Environment, Pick garbage **is **Action and Points earned **is Rewards.

#artificial-intelligence #machine-intelligence #data-science #machine-learning #reinforcement-learning

Reinforcement Learning — Reward Oriented Intelligence
1.25 GEEK