Markov decision process

A Markov decision process is a method for optimizing decision making over time in a step-by-step manner in situations where the outcomes of the decisions are partially random and partially determined by the decisions.

Markov Decision Process Media

• 

  Example of a simple MDP with three states (green circles) and two actions (orange circles), with two rewards (orange arrows)

• 

  Pole Balancing example (rendering of the environment from the Open AI gym benchmark)