3 papers
stat.ML2021
Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions
Kei Takemura, Shinji Ito, Daisuke Hatano +4
The contextual combinatorial semi-bandit problem with linear payoff functions is a decision-making problem in which a learner chooses a set of arms with the feature vectors in each…
cs.GT2019
Non-zero-sum Stackelberg Budget Allocation Game for Computational Advertising
Daisuke Hatano, Yuko Kuroki, Yasushi Kawase +3
Computational advertising has been studied to design efficient marketing strategies that maximize the number of acquired customers. In an increased competitive market, however, a m…
stat.ML2018
Causal Bandits with Propagating Inference
Akihiro Yabe, Daisuke Hatano, Hanna Sumita +4
Bandit is a framework for designing sequential experiments. In each experiment, a learner selects an arm and obtains an observation corresponding to . Theore…