Reinforcement Learning in AI
Artificial intelligence is growing exponentially. With an estimated market size of 7.35B US dollars. McKinsey predicts that AI techniques (including deep learning and reinforcement learning) have the potential to create between $3.5T and $5.8T in value annually.
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 reward. RL is one of the three basic Machine Learning (ML) paradigms, besides supervised learning and unsupervised learning.
RL is the training of ML models to make a sequence of decisions. The agent learns to achieve a goal in an uncertain environment. In RL, an agent faces a game-like situation. The computer employs trial and error to come up with a solution to the problem. To get the machine to do what the programmer wants, the AI agent gets either rewards/ penalties for the actions it performs. Its goal is to maximize the total reward. Although the designer sets the reward policy–that is, the rules of the game – he gives the model no hints/ suggestions for how to solve the game.
It’s up to the model to figure out how to perform the task to maximize the reward, starting from totally random trials and finishing with sophisticated tactics and superhuman skills. By leveraging the power of search and many trials, RL is currently the most effective way to hint machine’s creativity. In contrast to human beings, AI can gather experience from thousands of parallel gameplays if a reinforcement learning algorithm is run on a sufficiently powerful computer infrastructure.
E.g. AI agents developed by Google’s DeepMind beat human pros at Starcraft II — a first in the world of artificial intelligence. Games like Starcraft II are harder for computers to play than board games like chess or Go.