Assist-as-needed robotic trainer based on reinforcement learning and its application to dart-throwing.
Chihiro ObayashiTomoya TameiTomohiro ShibataPublished in: Neural Networks (2014)
Keyphrases
- reinforcement learning
- mobile robot
- real time
- model free
- function approximation
- robotic systems
- perception action
- multi agent
- computer vision
- learning algorithm
- optimal control
- machine learning
- real robot
- learning process
- robot control
- temporal difference learning
- robotic arm
- stochastic approximation
- object manipulation
- neural network