User-Interactive Offline Reinforcement Learning.
Phillip SwazinnaSteffen UdluftThomas A. RunklerPublished in: ICLR (2023)
Keyphrases
- reinforcement learning
- user interaction
- user interface
- real time
- user defined
- web interface
- user experience
- machine learning
- human friendly
- user centered
- user centric
- learning algorithm
- user satisfaction
- function approximation
- user feedback
- human users
- recommendation systems
- query formulation
- markov decision processes
- user input
- user preferences
- multiple users
- mixed initiative
- end users