Performance analysis of a new updating rule for TD(λ) learning in feedforward networks for position evaluation in Go game.
Horace Wai-kit ChanIrwin KingJohn C. S. LuiPublished in: ICNN (1996)
Keyphrases
- feed forward
- td learning
- back propagation
- artificial neural networks
- neural nets
- recurrent networks
- temporal difference
- neural network
- spiking neurons
- function approximation
- recurrent neural networks
- evaluation function
- hidden layer
- visual cortex
- adaptive neural
- reinforcement learning
- connectionist networks
- knowledge base