Login / Signup
Video Recommendation with Multi-gate Mixture of Experts Soft Actor Critic.
Dingcheng Li
Xu Li
Jun Wang
Ping Li
Published in:
SIGIR (2020)
Keyphrases
</>
actor critic
video sequences
reinforcement learning
policy gradient
temporal difference
optimal control
recommender systems
neuro fuzzy
approximate dynamic programming
decision making
convergence rate
evaluation function
reinforcement learning algorithms
gradient method