Deep Reinforcement Learning for Page-wise Recommendations.
Xiangyu ZhaoLong XiaLiang ZhangZhuoye DingDawei YinJiliang TangPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- website
- function approximation
- recommender systems
- web pages
- pairwise
- state space
- markov decision processes
- reinforcement learning algorithms
- learning problems
- learning algorithm
- deep learning
- action selection
- model free
- optimal control
- optimal policy
- dynamic programming
- learning process
- multi agent
- machine learning
- user preferences
- supervised learning
- social networks
- replacement policy
- reinforcement learning methods
- virtual memory
- multi agent reinforcement learning
- navigational patterns
- making recommendations
- navigational behavior