itlaw

Definition

Reinforcement learning is

“ [a]n approach to machine learning in which an agent learns to interact with its environment, receiving inputs, and making sequential decisions so as to maximise future rewards. An important feature in this context is that it is often only after the agent makes a number of decisions that it learns of the payoff resulting from the set of choices. One challenge in reinforcement is thus to work out which of the decisions were 'good' and which less so.[1] ”
“ a framework that shifts the focus of machine learning from pattern recognition to experience-driven sequential decision-making.[2] ”

Overview

"It promises to carry AI applications forward toward taking actions in the real world. While largely confined to academia over the past several decades, it is now seeing some practical, real-world successes."[3]

"Whereas traditional machine learning has mostly focused on pattern mining, reinforcement learning shifts the focus to decision making, and is a technology that will help AI to advance more deeply into the realm of learning about and executing actions in the real world. It has existed for several decades as a framework for experience-driven sequential decision-making, but the methods have not found great success in practice, mainly owing to issues of representation and scaling. However, the advent of deep learning has provided reinforcement learning with a 'shot in the arm.'"[4]

"RL algorithms learn by trial and error, being rewarded for reaching specified objectives — both for immediate actions and long-term goals. The emphasis on simulated motivation and learning from direct interaction with the environment, without requiring explicit examples and models, are among the characteristics that set RL apart from other ML approaches."

References

  1. ↑ Machine Learning: The Power and Promise of Computers That Learn by Example, at 123.
  2. ↑ One Hundred Year Study on Artificial Intelligence, at 9.
  3. ↑ Id.
  4. ↑ Id. at 15.