REVEAL 2020: Bandit and Reinforcement Learning from User Interactions.
Thorsten JoachimsYves RaimondOlivier KochMaria DimakopoulouFlavian VasileAdith SwaminathanPublished in: RecSys (2020)
Keyphrases
- user interaction
- reinforcement learning
- user feedback
- multi armed bandit
- user interface
- function approximation
- user behavior
- user studies
- user input
- state space
- user experience
- user model
- model free
- machine learning
- shape prior
- optimal policy
- multi agent
- interactive segmentation
- learning algorithm
- markov decision processes
- random sampling
- web users
- active learning
- artificial intelligence
- online video