Introduction to Reinforcement Learning

Machine learning is often divided into three categories: supervised, unsupervised, and reinforcement learning.  Reinforcement learning concerns problems with sequences of decisions (where each decision affects subsequent opportunities), in which the effects can be uncertain, and with potentially long-term goals.  It has achieved immense success in various different fields, especially AI/Robotics and Operations Research, by providing a framework for learning from interactions with an environment and feedback in the form of rewards and penalties.

Shane Conway, researcher at Kepos Capital, gives a general overview of reinforcement learning, covering how to solve cases where there is uncertainty both in actions and states, as well as where the state space is very large.  


This talk was given at the New York Open Statistical Programming Meetup.