Interactive Recommender Systems (IRS) have been increasingly used in var...
Off-policy learning, referring to the procedure of policy optimization w...
Autonomous exploration is one of the important parts to achieve the fast...
Template mining is one of the foundational tasks to support log analysis...
We generalize the multiple-play multi-armed bandits (MP-MAB) problem wit...
Registration is a basic yet crucial task in point cloud processing. In
c...
Multi-player multi-armed bandits (MMAB) study how decentralized players
...
Autonomous exploration is one of the important parts to achieve the
auto...
As a model-free optimization and decision-making method, deep reinforcem...
A fundamental question for companies is: How to make good decisions with...
Contextual bandit algorithms have gained increasing popularity in recomm...
Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTM),...
Word representations are created using analogy context-based statistics ...
Emerging new applications demand the current Internet to provide new
fun...