Task Decoupling in Preference-based Reinforcement Learning for Personalized Human-Robot Interaction.
Mingjiang LiuChunlin ChenPublished in: IROS (2022)
Keyphrases
- human robot interaction
- reinforcement learning
- human robot
- gesture recognition
- human centered
- input output
- e learning
- multi agent
- function approximation
- humanoid robot
- robot programming
- service robots
- learning process
- context aware
- markov decision processes
- pointing gestures
- user profiles
- state space
- learning algorithm
- model free
- temporal difference
- reinforcement learning algorithms
- multi modal
- dynamic programming
- machine learning
- neural network
- user preferences
- human computer interaction
- manipulation tasks
- qualitative spatial