Nice choice — starting at the foundations

We’ll build the formal MDP setup and then derive the Bellman equations step by step. Reminder: the Bellman relation links a state's value to immediate reward plus the expected discounted value of successor states under a policy.

Match key MDP items to their definitions or equations

Match each term on the left with the best definition or equation on the right.

Match the MDP term to its definition or equation.Markov propertyPolicy πValue function V^π(s)Bellman optimality equation (for V* or Q*)

How was this question for you?

Too easyAbout rightToo hard

Learning: Reinforcement Learning