User-Interactive Offline Reinforcement Learning.
Phillip SwazinnaSteffen UdluftThomas A. RunklerPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- user interaction
- real time
- user interface
- function approximation
- end users
- user satisfaction
- graphical user interfaces
- web interface
- multi agent
- user feedback
- user profiles
- mixed initiative
- model free
- user model
- user experience
- markov decision processes
- transfer learning
- user queries
- collaborative filtering
- state space
- information systems
- social networks
- learning algorithm
- information retrieval