Approximate Dynamic Programming and Neural Networks on Game Hardware.
Ryan J. MeuthDonald C. Wunsch IIPublished in: IJCNN (2007)
Keyphrases
- approximate dynamic programming
- neural network
- linear program
- reinforcement learning
- stochastic dynamic programming
- dynamic programming
- game play
- video games
- computer games
- control policy
- artificial neural networks
- step size
- nash equilibrium
- average cost
- policy iteration
- genetic algorithm
- evolutionary algorithm
- least squares
- convergence rate
- image processing