On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems.
Siyu WangXiaocong ChenLina YaoPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- recommender systems
- learning problems
- prior knowledge
- hierarchical reinforcement learning
- temporal difference learning
- learning systems
- online learning
- collaborative filtering
- supervised learning
- state space
- dynamic programming
- active learning
- image representation
- learning tasks
- function approximation
- state action
- hidden state
- policy search