Keyphrases
- dynamic programming
- neural network
- actor critic
- optimal control
- approximate dynamic programming
- reinforcement learning
- policy gradient
- video games
- artificial neural networks
- gradient method
- temporal difference
- state space
- objective function
- policy iteration
- feed forward
- linear programming
- least squares
- infinite horizon
- nash equilibrium
- function approximation
- stochastic games
- recurrent neural networks
- dynamic environments