Reinforcement learning for content's customization: a first step of experimentation in Skyscanner.
Chiara GiachinoLuigi BollaniAlessandro BonadonnaMarco BertettiPublished in: Ind. Manag. Data Syst. (2021)
Keyphrases
- reinforcement learning
- metadata
- user interface
- learning algorithm
- state space
- web content
- textual content
- function approximation
- post processing
- multimedia
- dynamic programming
- digital content
- temporal difference
- reinforcement learning algorithms
- multi agent reinforcement learning
- learning objects
- optimal policy
- transfer learning
- mobile robot
- multimedia content
- optimal control
- user generated content
- user generated
- content and structure
- policy search