Related papers: On Transportability for Structural Causal Bandits
In this paper, we investigate the impact of context diversity on stochastic linear contextual bandits. As opposed to the previous view that contexts lead to more difficult bandit learning, we show that when the contexts are sufficiently…
Contextual bandits serve as a fundamental model for many sequential decision making tasks. The most popular theoretically justified approaches are based on the optimism principle. While these algorithms can be practical, they are known to…
Contextual bandit algorithms -- a class of multi-armed bandit algorithms that exploit the contextual information -- have been shown to be effective in solving sequential decision making problems under uncertainty. A common assumption…
We propose a novel framework for structured bandits, which we call an influence diagram bandit. Our framework captures complex statistical dependencies between actions, latent variables, and observations; and thus unifies and extends many…
We study the problem of learning 'good' interventions in a stochastic environment modeled by its underlying causal graph. Good interventions refer to interventions that maximize rewards. Specifically, we consider the setting of a…
Thanks to the power of representation learning, neural contextual bandit algorithms demonstrate remarkable performance improvement against their classical counterparts. But because their exploration has to be performed in the entire neural…
Contextual bandit algorithms often estimate reward models to inform decision-making. However, true rewards can contain action-independent redundancies that are not relevant for decision-making. We show it is more data-efficient to estimate…
We consider contextual linear bandits over networks, a class of sequential decision-making problems where learning occurs simultaneously across multiple locations and the reward distributions share structural similarities while also…
Structured stochastic multi-armed bandits provide accelerated regret rates over the standard unstructured bandit problems. Most structured bandits, however, assume the knowledge of the structural parameter such as Lipschitz continuity,…
We study collaborative learning in multi-agent Bayesian bandit problems, where strategic agents collectively solve the same bandit instance. While multiple agents can accelerate learning by sharing information, strategic agents might prefer…
We propose a new sequential decision-making setting, combining key aspects of two established online learning problems with bandit feedback. The optimal action to play at any given moment is contingent on an underlying changing state which…
Individual decision-makers consume information revealed by the previous decision makers, and produce information that may help in future decisions. This phenomenon is common in a wide range of scenarios in the Internet economy, as well as…
We consider a novel variant of the contextual bandit problem (i.e., the multi-armed bandit with side-information, or context, available to a decision-maker) where the context used at each decision may be corrupted ("useless context"). This…
We study regret minimization in causal bandits under causal sufficiency where the underlying causal structure is not known to the agent. Previous work has focused on identifying the reward's parents and then applying classic bandit methods…
We propose a contextual bandit based model to capture the learning and social welfare goals of a web platform in the presence of myopic users. By using payments to incentivize these agents to explore different items/recommendations, we show…
Bandits with covariates, a.k.a. contextual bandits, address situations where optimal actions (or arms) at a given time $t$, depend on a context $x_t$, e.g., a new patient's medical history, a consumer's past purchases. While it is…
We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised learning representations. We prove that it works in a…
We study learning to learn for the multi-task structured bandit problem where the goal is to learn a near-optimal algorithm that minimizes cumulative regret. The tasks share a common structure and an algorithm should exploit the shared…
In this paper, the causal bandit problem is investigated, with the objective of maximizing the long-term reward by selecting an optimal sequence of interventions on nodes in an unknown causal graph. It is assumed that both the causal…
We consider the contextual bandit problem where at each time, the agent only has access to a noisy version of the context and the error variance (or an estimator of this variance). This setting is motivated by a wide range of applications…