RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems.
Jiahong ZhouShunhui MaoGuoliang YangBo TangQianlong XieLebin LinXingxing WangDong WangPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- recommender systems
- function approximation
- reinforcement learning algorithms
- state space
- rl algorithms
- collaborative filtering
- model free
- matrix factorization
- markov decision processes
- optimal policy
- temporal difference
- learning algorithm
- machine learning
- learning problems
- user profiles
- dynamic programming
- approximate dynamic programming
- control problems
- action selection
- autonomous learning
- optimal control
- resource allocation
- user preferences
- user modeling
- principal component analysis
- supervised learning
- multi agent
- transfer learning
- learning capabilities
- cold start problem
- continuous state
- policy evaluation
- reinforcement learning methods
- direct policy search
- partially observable domains
- exploration exploitation
- policy search
- action space
- user model
- learning classifier systems