Related papers: Federated Combinatorial Multi-Agent Multi-Armed Ba…
Offline reinforcement learning (RL), which seeks to learn an optimal policy using offline data, has garnered significant interest due to its potential in critical applications where online data collection is infeasible or expensive. This…
This paper considers the problem of combinatorial multi-armed bandits with semi-bandit feedback and a cardinality constraint on the super-arm size. Existing algorithms for solving this problem typically involve two key sub-routines: (1) a…
In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of interest is regret, defined as the gap between the expected…
Modern systems, such as digital platforms and service systems, increasingly rely on contextual bandits for online decision-making; however, their deployment can inadvertently create unfair exposure among arms, undermining long-term platform…
There is a rapid increase in the cooperative learning paradigm in online learning settings, i.e., federated learning (FL). Unlike most FL settings, there are many situations where the agents are competitive. Each agent would like to learn…
We present an online tutoring system that learns to provide effective feedback to students after they answer questions incorrectly. Using data from one million students, the system learns which assistance action (e.g., one of multiple…
Multi-armed bandits (MAB) is a sequential decision-making model in which the learner controls the trade-off between exploration and exploitation to maximize its cumulative reward. Federated multi-armed bandits (FMAB) is an emerging…
Motivated by problems in search and detection we present a solution to a Combinatorial Multi-Armed Bandit (CMAB) problem with both heavy-tailed reward distributions and a new class of feedback, filtered semibandit feedback. In a CMAB…
We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…
We consider the problem of asynchronous online combinatorial optimization on a network of communicating agents. At each time step, some of the agents are stochastically activated, requested to make a prediction, and the system pays the…
The performance of large language models (LLMs) is highly sensitive to the input prompt, making prompt optimization a critical task. However, real-world application is hindered by three major challenges: (1) the black-box nature of powerful…
The design of personalized incentives or recommendations to improve user engagement is gaining prominence as digital platform providers continually emerge. We propose a multi-armed bandit framework for matching incentives to users, whose…
Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theoretical guarantees. We reformulate it as an online learning…
This work establishes the first framework of federated $\mathcal{X}$-armed bandit, where different clients face heterogeneous local objective functions defined on the same domain and are required to collaboratively figure out the global…
Motivated by applications such as online labor markets we consider a variant of the stochastic multi-armed bandit problem where we have a collection of arms representing strategic agents with different performance characteristics. The…
Influence maximization, adaptive routing, and dynamic spectrum allocation all require choosing the right action from a large set of alternatives. Thanks to the advances in combinatorial optimization, these and many similar problems can be…
We develop a novel and generic algorithm for the adversarial multi-armed bandit problem (or more generally the combinatorial semi-bandit problem). When instantiated differently, our algorithm achieves various new data-dependent regret…
In combinatorial semi-bandits, a learner repeatedly selects from a combinatorial decision set of arms, receives the realized sum of rewards, and observes the rewards of the individual selected arms as feedback. In this paper, we extend this…
Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks against these learning…
Sequential decision-making under uncertainty often involves multiple agents learning which actions (arms) yield the highest rewards through repeated interaction with a stochastic environment. This setting is commonly modeled by cooperative…