Learning a Structured Neural Network Policy for a Hopping Task.
Julian ViereckJules KozolinskyAlexander HerzogLudovic RighettiPublished in: IEEE Robotics Autom. Lett. (2018)
Keyphrases
- neural network
- learning systems
- structured output
- reinforcement learning
- prior knowledge
- online learning
- neural nets
- learning process
- knowledge acquisition
- learning rules
- structured learning
- feed forward
- learning tasks
- unsupervised learning
- pattern recognition
- policy gradient
- back propagation
- incremental learning
- learning algorithm
- machine learning