Multi-objective Meta-return Reinforcement Learning for Sequential Recommendation.
Yemin YuKun KuangJiangchao YangZeke WangKunyang JiaWeiming LuHongxia YangFei WuPublished in: CICAI (2) (2022)
Keyphrases
- multi objective
- reinforcement learning
- evolutionary algorithm
- multi objective optimization
- optimization algorithm
- objective function
- multiple objectives
- state space
- multiobjective optimization
- recommender systems
- collaborative filtering
- reinforcement learning algorithms
- learning algorithm
- evolutionary optimization
- pareto optimal
- conflicting objectives
- nsga ii
- multi objective optimization problems
- machine learning
- genetic algorithm
- bi objective
- function approximation
- multi objective evolutionary
- particle swarm optimization
- multi agent
- optimum design
- multiobjective evolutionary algorithm
- multi objective evolutionary algorithms
- multi objective genetic algorithms
- recommendation systems
- optimal policy
- personalized recommendation
- markov decision process
- temporal difference
- model free
- meta level
- user feedback
- learning problems
- robotic control
- dynamic programming