Approximate Dynamic Programming¶
Powell, W. B. (2011). Approximate Dynamic Programming: Solving the Curses of Dimensionality. Wiley.
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Dynamic Programming
- Powell (2011) and modern deep-RL algorithms (DQN, AlphaGo, MuZero) represent the latest evolution of approximate DP, where neural-network value functions approximate the Bellman optimality equation.
This sourceDefinitive treatment of approximate DP: integrates MDPs, mathematical programming, simulation, and statistics, organizing policies (myopic, lookahead, policy-function-approximation, value-function-approximation) to scale Bellman-equation solutions via function approximation
- Powell (2011) and modern deep-RL algorithms (DQN, AlphaGo, MuZero) represent the latest evolution of approximate DP, where neural-network value functions approximate the Bellman optimality equation.
- Resource Management
- Listed in the references but not attached to a specific claim.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:f113fcc364e9 · see in the full table