Bellman equation

E1288433 UNEXPLORED

The Bellman equation is a fundamental recursive relationship in dynamic programming and reinforcement learning that expresses the value of a decision problem in terms of immediate rewards plus the expected value of subsequent states.

All labels observed (6)

How this entity was disambiguated

Referenced by (11)

Full triples — surface form annotated when it differs from this entity's canonical label.

Deep Q-Learning → uses → Bellman equation ⓘ
Richard Bellman → fieldOfWork → dynamic programming ⓘ
subject linked to: Bellman
linked to: Bellman equation
Richard Bellman → notableConcept → Bellman equation ⓘ
subject linked to: Bellman
Q-learning → usesUpdateRule → Bellman optimality equation ⓘ
linked to: Bellman equation
Recursive Methods in Economic Dynamics → topic → Bellman equation ⓘ
Recursive Methods in Economic Dynamics → usesMethod → Bellman operator ⓘ
linked to: Bellman equation
Optimization over Time → topic → Bellman equations ⓘ
linked to: Bellman equation
Richard E. Bellman → notableWork → Bellman equation ⓘ
Richard E. Bellman → notableIdea → Bellman optimality principle ⓘ
linked to: Bellman equation
Neural Fitted Q-Iteration → usesTarget → Bellman optimality equation ⓘ
subject linked to: neural fitted Q-iteration (NFQ)
linked to: Bellman equation
Recursive Macroeconomic Theory → approach → Bellman equation ⓘ