Markov Decision Process

A mathematical model for sequential decision-making under uncertainty defined by a tuple (S, A, P, R, γ): state space S, action set A, transition kernel P(s'|s,a), reward function R(s,a), and discount factor γ; decisions (policies) map states to actions or distributions over actions.

A formal model for sequential decision problems in which an agent observes a state from a state space, chooses an action from an action set, and the system transitions to a next state according to transition probabilities that depend only on the current state and action (the Markov property); a reward function assigns immediate payoffs and the objective is to maximize expected cumulative reward ov