Related papers: Risk-Aware Continuous Control with Neural Contextu…
Precision oncology, the genetic sequencing of tumors to identify druggable targets, has emerged as the standard of care in the treatment of many cancers. Nonetheless, due to the pace of therapy development and variability in patient…
We propose a new risk-constrained reformulation of the standard Linear Quadratic Regulator (LQR) problem. Our framework is motivated by the fact that the classical (risk-neutral) LQR controller, although optimal in expectation, might be…
The bandit paradigm provides a unified modeling framework for problems that require decision-making under uncertainty. Because many business metrics can be viewed as rewards (a.k.a. utilities) that result from actions, bandit algorithms…
This paper introduces a new principled approach for off-policy learning in contextual bandits. Unlike previous work, our approach does not derive learning principles from intractable or loose bounds. We analyse the problem through the…
To address the contextual bandit problem, we propose an online random forest algorithm. The analysis of the proposed algorithm is based on the sample complexity needed to find the optimal decision stump. Then, the decision stumps are…
Early-phase clinical trials face the challenge of selecting optimal drug doses that balance safety and efficacy due to uncertain dose-response relationships and varied participant characteristics. Traditional randomized dose allocation…
Ensuring safety in autonomous driving requires precise, real-time risk assessment and adaptive behavior. Prior work on risk estimation either outputs coarse, global scene-level metrics lacking interpretability, proposes indicators without…
In this paper we consider the adversarial contextual bandit problem in metric spaces. The paper "Nearest neighbour with bandit feedback" tackled this problem but when there are many contexts near the decision boundary of the comparator…
A key goal in stochastic contextual linear bandits is to efficiently learn a near-optimal policy. Prior algorithms for this problem learn a policy by strategically sampling actions but naively (passively) sampling contexts from the…
We address the problem of learning in an online, bandit setting where the learner must repeatedly select among $K$ actions, but only receives partial feedback based on its choices. We establish two new facts: First, using a new algorithm…
There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are…
Bandits with feedback graphs are powerful online learning models that interpolate between the full information and classic bandit problems, capturing many real-life applications. A recent work by Zhang et al. (2023) studies the contextual…
The matrix contextual bandit (CB), as an extension of the well-known multi-armed bandit, is a powerful framework that has been widely applied in sequential decision-making scenarios involving low-rank structure. In many real-world…
Contextual multi-armed bandits provide powerful tools to solve the exploitation-exploration dilemma in decision making, with direct applications in the personalized recommendation. In fact, collaborative effects among users carry the…
We study the stream-based online active learning in a contextual multi-armed bandit framework. In this framework, the reward depends on both the arm and the context. In a stream-based active learning setting, obtaining the ground truth of…
Reinforcement learning (RL) agents are commonly trained and evaluated in the same environment. In contrast, humans often train in a specialized environment before being evaluated, such as studying a book before taking an exam. The potential…
Safety is a critical concern when deploying reinforcement learning agents for realistic tasks. Recently, safe reinforcement learning algorithms have been developed to optimize the agent's performance while avoiding violations of safety…
Causal knowledge can be used to support decision-making problems. This has been recognized in the causal bandits literature, where a causal (multi-armed) bandit is characterized by a causal graphical model and a target variable. The arms…
We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying learning signal may be different between these two data…
In real-world streaming recommender systems, user preferences often dynamically change over time (e.g., a user may have different preferences during weekdays and weekends). Existing bandit-based streaming recommendation models only consider…