Federated Reinforcement Learning for Fast Personalization.
Chetan NadigerAnil KumarSherine AbdelhakPublished in: AIKE (2019)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- user modeling
- markov decision processes
- reinforcement learning algorithms
- user profiling
- recommender systems
- optimal policy
- learning process
- machine learning
- temporal difference learning
- user model
- web personalization
- user profiles
- collaborative filtering
- dynamic adaptation
- data sources
- digital libraries
- learning algorithm
- data sets
- transition model
- policy search
- robot control
- partially observable
- temporal difference
- learning classifier systems
- learning problems
- supervised learning
- multi agent
- genetic algorithm