A Soft Actor-Critic Algorithm for Sequential Recommendation.
Hyejin HongYusuke KimuraKenji HatanoPublished in: DEXA (1) (2024)
Keyphrases
- monte carlo
- learning algorithm
- actor critic
- dynamic programming
- k means
- np hard
- optimal solution
- neural network
- simulated annealing
- convergence proof
- mathematical model
- optimization algorithm
- linear programming
- collaborative filtering
- cost function
- machine learning
- optimal control
- temporal difference learning
- approximate dynamic programming
- computational complexity