Computers Can Now Do Things No Programmer Could Teach Them!

Reinforcement Learning has recently become a branch of Artificial Intelligence. This process duplicates an exceptionally basic rule from nature, which is the tendency to associate a certain behavior with the desired outcome.
Some of the earliest artificial-intelligence researchers believed that this type of association can be usefully reproduced in machines. In 1951, a student at Harvard University built a machine that used a simple form of reinforcement learning to mimic a rat learning to navigate a maze.
An example of Artificial Intelligence using Reinforcement Learning is AlphaGo, a computer created by a backup of Alphabet called DeepMind. The Artificial Intelligence program (AlphaGo) was able to master a complex table game called Go, in which he beat the top human players in the world.
Researchers at Google worked with DeepMind to use deep reinforcement learning to make its data centers more energy-efficient. These days, the Reinforcement Learning concept is being used in different industries, especially on cars for self-parking and even to the extent of interacting with human drivers, such as traffic circles or four-way stops.
To learn more about this, click the photo.