{"id":8416,"date":"2019-08-09T12:48:43","date_gmt":"2019-08-09T19:48:43","guid":{"rendered":"https:\/\/www.springboard.com\/?p=8416"},"modified":"2023-09-28T00:49:22","modified_gmt":"2023-09-28T07:49:22","slug":"reinforcement-learning","status":"publish","type":"post","link":"https:\/\/www.springboard.com\/blog\/data-science\/reinforcement-learning\/","title":{"rendered":"What Is Reinforcement Learning?"},"content":{"rendered":"\n

In real life, all of our routine learning, predicting, and decision-making runs on reinforcement learning. It makes sense, then, that scientists build machines using this principle too.<\/span><\/p>\n\n\n\n

Reinforcement Learning Defined<\/span><\/h2>\n\n\n\n

Here is a simple definition: Think of reinforcement learning as any type of learning that comes about through, and is reinforced by, either positive or negative stimuli. These stimuli either cause you to adopt, retain, or stop a certain habit.<\/span><\/p>\n\n\n\n

For example, when you mastered the alphabet, you were likely rewarded with hearty compliments from your teacher. You felt good: “Hey, I did it!” Your teacher incrementally rewarded you each small step along the way until you learned how to read. <\/span><\/p>\n\n\n\n

That’s reinforced learning<\/span>\u2014<\/span>where you learned something in life, reinforced through feedback.<\/span><\/p>\n\n\n\n

Reinforced Learning: The Model<\/span><\/h2>\n\n\n\n

In practice, the reinforcement learning model looks like this:<\/span><\/p>\n\n\n\n

\"reinforcement<\/figure>\n\n\n\n

You, as the agent, are in a particular <\/span>situation<\/span><\/i> (state S), you adopt a specific <\/span>action<\/span><\/i> (A) to achieve your goal, and you receive your feedback in the shape of <\/span>punishment<\/span><\/i> or <\/span>reward<\/span><\/i> (R). <\/span><\/p>\n\n\n\n

Reinforcement learning, in other words, is a system of trial and error that comes through interaction with your environment.<\/span><\/p>\n\n\n\n

Data scientists<\/a> use these same reinforcement learning principles for programming algorithms to perform tasks.<\/span><\/p>\n\n\n\n

How Machine Reinforcement Learning Works<\/span><\/h2>\n\n\n\n

Translated to the machine learning world, what you have is a system of trial and error, where the algorithm, or agent, learns from missteps in its simulated environment and gets rewarded after each small success.<\/span><\/p>\n\n\n\n

The algorithm is often led through various probabilistic models until programmers find the one that is the most effective. This is the model where the algorithm makes the fewest mistakes and gets the greatest number of rewards in the shortest period of time.<\/span><\/p>\n\n\n\n

Industries That Use Machine Reinforcement Learning<\/span><\/h2>\n\n\n\n

Some of the industries that commonly utilize machine reinforcement learning include the following:<\/span><\/p>\n\n\n\n

Internet advertising <\/b><\/p>\n\n\n\n

Online companies like Facebook use machine learning and data science<\/a> process to analyze your preferences, background, and online behavior patterns so they can direct relevant ads your way. Since your habits and preferences tend to change, researchers use an algorithm called the <\/span>deep Q-learning method<\/b> (more on that later) to constantly update those ads.<\/span><\/p>\n\n\n\n

Gaming<\/b><\/p>\n\n\n\n

Reinforcement learning is the principle behind gaming. Let’s take <\/span>Pac-Man<\/span><\/a> for instance. In the classic video game, our friendly yellow hero has to gobble all the ghosts in the grid without being touched by them before the player can advance to the next stage. A perfect Pac-Man game is where the player scores maximum points in achieving this feat in the shortest amount of time. <\/span><\/p>\n\n\n\n

All games are premised on similar reinforcement learning principles.<\/span><\/p>\n\n\n\n

Finance<\/b><\/p>\n\n\n\n

Reinforcement learning is used in the finance industry in various ways. One example is trading, where algorithms are trained to forecast market behavior. IBM, for instance, built a financial trading system on its <\/span>Data Science Experience<\/span><\/a> platform (now called <\/span>Watson Studio<\/span><\/a>) that uses reinforcement learning to develop algorithms for calculating the profits and losses of industries.<\/span><\/p>\n\n\n\n

Robotics<\/b><\/p>\n\n\n\n

Programmers use reinforcement learning to train robots. Sophisticated algorithms that program robot behavior are developed in controlled environments and led through sequential actions to complete a particular task. Values are accorded for each success, and algorithms are rated successful based on their maximum cumulative rewards, or values. Such deep reinforcement learning methods teach four-legged robots (for instance) how to recover when they fall.<\/span><\/p>\n\n\n\n

Vehicular navigation<\/b><\/p>\n\n\n\n

Reinforcement learning is used for training driverless vehicles. U.K.-based <\/span>Wayve<\/span><\/a>, for example, taught its autonomous vehicles to drive independently within 15-20 minutes. A human driver was placed in the car to intervene when necessary. The underlying algorithms used different trial and error situations for finding the best model that would help the vehicle complete its drive without accidents or intervention. <\/span><\/p>\n\n\n\n

Other industries that use reinforcement learning include:<\/b><\/p>\n\n\n\n