Delayed Rewards in the Context of Reinforcement Learning based Recommender Systems.
Debmalya BiswasPublished in: AAI4H@ECAI (2020)
Keyphrases
- reinforcement learning
- recommender systems
- markov decision processes
- contextual information
- context sensitive
- function approximation
- reinforcement learning algorithms
- dynamic programming
- implicit feedback
- temporal difference
- context dependent
- collaborative filtering
- user model
- context aware
- optimal control
- context awareness
- supervised learning
- learning process
- partially observable
- neural network