Value Function

Intermediate

Expected cumulative reward from a state or state-action pair.

Full Definition

Expected cumulative reward from a state or state-action pair.

Keywords

expected return

Domains

AI Economics & Strategy

Related Terms

Reinforcement Learning used in

A learning paradigm where an agent interacts with an environment and learns to choose actions to maximize cumulative ...

 Q-Function narrower than

Expected return of taking action in a state.

 Bellman Equation prerequisite of

Fundamental recursive relationship defining optimal value functions.

 Q-Function related to

Expected return of taking action in a state.

 Bellman Equation related to

Fundamental recursive relationship defining optimal value functions.

 Policy Gradient related to

Optimizing policies directly via gradient ascent on expected reward.

 Actor-Critic related to

Combines value estimation (critic) with policy learning (actor).

 Markov Decision Process related to

Formal framework for sequential decision-making under uncertainty.

 State Space related to

All possible configurations an agent may encounter.

 Action Space related to

Set of all actions available to the agent.

 Policy related to

Strategy mapping states to actions.

Concept Map

See how Value Function connects to other concepts.

Open Knowledge Graph