Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning.
Stefan ElfwingEiji UchibeKenji DoyaPublished in: CoRR (2017)
Keyphrases
- function approximation
- function approximators
- reinforcement learning
- neural network
- temporal difference learning algorithms
- radial basis function
- temporal difference
- activation function
- temporal difference learning
- mackey glass
- reinforcement learning algorithms
- reinforcement learning problems
- model free
- learning tasks
- mountain car
- hidden layer
- artificial neural networks
- state space
- reinforcement learning methods
- td learning
- learning algorithm
- optimal control
- recurrent neural networks
- training data
- rbf network
- monte carlo
- optimal policy
- policy search
- machine learning algorithms
- multi agent
- genetic algorithm
- temporal difference methods
- machine learning