Training a deep policy gradient-based neural network with asynchronous learners on a simulated robotic problem.
Winfried LötzschJulien VitayFred H. HamkerPublished in: GI-Jahrestagung (2017)
Keyphrases
- neural network
- training algorithm
- feed forward neural networks
- training process
- feedforward neural networks
- neural network training
- backpropagation algorithm
- multi layer perceptron
- training patterns
- medical students
- back propagation
- learning activities
- train a neural network
- e learning
- learning environment
- feed forward
- learning materials
- training set
- real time
- mobile robot
- artificial neural networks
- discussion forums
- learning systems
- genetic algorithm
- recurrent networks
- activation function
- asynchronous learning
- learning styles
- online discussion
- fuzzy logic
- online learning
- training samples
- collaborative learning
- recurrent neural networks
- multilayer perceptron
- neural network model
- optimal policy
- learning strategies
- self organizing maps
- deep architectures
- decision trees
- learning experience
- real robot
- fault diagnosis
- learning processes
- learning outcomes
- learning resources
- hidden layer
- supervised learning
- multi layer
- learning community