Random-TD Function Approximator.
Hassab Elgawi OsmanPublished in: J. Adv. Comput. Intell. Intell. Informatics (2009)
Keyphrases
- function approximators
- temporal difference
- function approximation
- reinforcement learning
- temporal difference methods
- temporal difference learning
- reinforcement learning algorithms
- td learning
- reinforcement learning problems
- evaluation function
- monte carlo
- td methods
- model free
- action selection
- neural network
- policy evaluation
- policy search
- learning algorithm
- real valued
- radial basis function
- action space
- markov decision problems
- supervised learning
- step size
- policy iteration
- optimal policy
- genetic programming
- reinforcement learning methods
- evolutionary methods
- state space
- active learning