A simulator for reinforcement learning training in the recommendation field.
Guangyao PangXiaoying ZhuKeda LuZizhen PengWeitao DengPublished in: ISPA/BDCloud/SocialCom/SustainCom (2020)
Keyphrases
- reinforcement learning
- state space
- recommender systems
- training phase
- training process
- function approximation
- supervised learning
- optimal control
- markov decision processes
- reinforcement learning algorithms
- multi agent
- online learning
- training samples
- real robot
- neural network
- model free
- user preferences
- dynamic programming
- artificial neural networks
- training set
- support vector
- artificial intelligence
- learning algorithm
- data mining