Reinforcement Learning

By experimenting, computers are figuring out how to do things that no programmer could teach them. Availability: 1 to 2 years

https://www.technologyreview.com/s/603501/10-breakthrough-technologies-2017-reinforcement-learning/

         As technology keeps advancing daily, developers, and consumers become hesitant on the topic of one of the biggest issues regarding innovation, artificial intelligence. According to the Merrin Dictionary, “Artificial intelligence is the theory and development of computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.” This sparks much debate that relates to this theory which is the approach known as reinforcement learning. All of us know the AlphaGo computer that was developed to master the impossibly complex board game Go which beat one of the best human players in the world in a high-profile match last year, which was programmed based on this approach of reinforcement learning. Stated by Knight, “reinforcement learning may soon inject greater intelligence into much more than games. In addition to improving self-driving cars, the technology can get a robot to grasp objects it has never seen before, and it can figure out the optimal configuration for the equipment in a data center.”

      What is fascinating to me is that this type of approach to learning is involved in our everyday lives. As it is becoming more powerful, it is still based on the “very simple principle from nature. The psychologist Edward Thorndike documented it more than 100 years ago.” As a brief history lesson given by Thorndike, it was soon adapted to be used as a process used by researchers at the prestigious college of Harvard and MIT.

Personally, reading about this advancement in how reinforcement learning has changed dramatically over history has marked new imagination and curiosity regarding the history of computers. “In March of 2016, ALphaGo, a program training using reinforcement learning, destroyed one of the best Go players of all time, South Korea’s Lee Sedol.” This was extremely surprising to the world because it meant that a program beat human skills just with conventional programming. This is sparking new interests in intelligence world which machines such as IBM’s Watson projecting precise data ranging from winners of a tennis match to what the exact temperature will be in the coming week. This breakthrough has sparked many new industries to think critically and like a human which has become so formidable.

Written by Mia Gradelski, Junior Student Help Desk

Author: miag19bronxvilleschoolorg

Bronxville Student Help desk contributor/writer.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s