Implementing Temporal-Difference Learning with the Scaled Conjugate Gradient Algorithm.
Tasos FalasAndreas StafylopatisPublished in: Neural Process. Lett. (2005)
Keyphrases
- temporal difference learning
- conjugate gradient algorithm
- fixed point
- function approximation
- evaluation function
- reinforcement learning
- game playing
- conjugate gradient
- temporal difference
- learning rate
- reinforcement learning algorithms
- markov decision process
- regularization framework
- policy iteration
- function approximators
- semi supervised learning
- prior knowledge