A mathematical model of sequential decision-making under uncertainty, in which an agent chooses actions that move it between states, receiving rewards along the way, with the next state depending only on the current state and action; the formal framework underlying most reinforcement learning.
Facts
Core PrincipleA mathematical model for sequential decision making when outcomes are uncertain. 1 Connections
Sources
1. Markov decision process - Wikipedia
Lead paragraphQuote, Lead paragraph
A Markov decision process (MDP) is a mathematical model for sequential decision making when outcomes are uncertain.
Reader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.
Sign in to dispute this or suggest a correction.