A value function assigns each dynamic programming state and time the best objective function value attainable over the remaining decisions. It is a score, whereas a control policy specifies the actions producing that score. In the 0-1 knapsack problem above, is the score, and choosing the items of weights and attains it. In sequential mathematical optimization, the Bellman equation computes a value function by comparing immediate reward plus continuation value. Use a supremum or infimum when the best score need not be attained by any admissible control policy.
In the context of reinforcement learning and decision making, a **value function** is a function that estimates the expected return (or future rewards) that an agent can achieve from a given state or state-action pair. It plays a fundamental role in evaluating the optimality of policies, guiding the agent's decisions as it seeks to maximize its cumulative rewards over time.
The function being maximized in a optimization problem.
New to topics? Read the docs here!