Deep Reinforcement Learning with Hidden Layers on Future States.
Hirotaka KamekoJun SuzukiNaoki MizukamiYoshimasa TsuruokaPublished in: CGW@IJCAI (2017)
Keyphrases
- hidden layer
- reinforcement learning
- perceptual aliasing
- back propagation
- feedforward neural networks
- feed forward neural networks
- neural network
- artificial neural networks
- function approximation
- radial basis function
- rbf neural network
- feed forward
- machine learning
- recurrent neural networks
- state space
- learning algorithm
- neural nets
- multilayer perceptron
- learning rate
- dynamic programming
- pattern recognition
- artificial intelligence
- number of hidden layers