Intrinsically motivated reinforcement learning for human-robot interaction in the real-world.
Ahmed Hussain QureshiYutaka NakamuraYuichiro YoshikawaHiroshi IshiguroPublished in: CoRR (2018)
Keyphrases
- human robot interaction
- reinforcement learning
- real world
- human robot
- robot programming
- human centered
- gesture recognition
- synthetic data
- service robots
- pointing gestures
- humanoid robot
- data sets
- wide range
- markov decision processes
- function approximation
- case study
- learning algorithm
- optimal policy
- state space
- hidden markov models
- qualitative spatial
- data mining
- multi agent
- three dimensional
- artificial intelligence
- machine learning