Revenue management (RM) is the application of analytical methodologies and tools that
predict consumer behavior and optimize product availability and prices to maximize a firm's …

Motivated by practical needs such as large-scale learning, we study the impact of adaptivity
constraints to linear contextual bandits, a central problem in online learning and decision …

In this paper, we study the episodic reinforcement learning (RL) problem modeled by finite-
horizon Markov Decision Processes (MDPs) with constraint on the number of batches. The …

Online learning in large-scale structured bandits is known to be challenging due to the curse
of dimensionality. In this paper, we propose a unified meta-learning framework for a wide …

We consider the classical stochastic multi-armed bandit problem with a constraint on the
total cost incurred by switching between actions. Under the unit switching cost structure …

While learning in an unknown Markov Decision Process (MDP), an agent should trade off
exploration to discover new information about the MDP, and exploitation of the current …

In this paper, we study the problem of regret minimization for episodic Reinforcement
Learning (RL) both in the model-free and the model-based setting. We focus on learning …

Out of the rich family of generalized linear bandits, perhaps the most well studied ones are
logistic bandits that are used in problems with binary rewards: for instance, when the learner …

Contextual multinomial logit (MNL) bandits capture many real-world assortment
recommendation problems such as online retailing/advertising. However, prior work has …

In many sequential decision making applications, the change of decision would bring an
additional cost, such as the wear-and-tear cost associated with changing server status. To …