SOURCE-LINKED INTELLIGENCE

Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Contextual bandits are a standard framework for sequential decision-making under uncertainty, with applications in clinical trials, dosage selection, recommendation systems, and autonomous systems. Safety is central in many of these applications, since a single unsafe decision in settings such as dosage selection or autonomous driving can have catastrophic consequences. A common way to model safety in bandit problems is to associate each action with both a reward signal and a cost signal, and to optimize reward subject to constraints on cost. Most existing safety-constrained bandit models enfo

Read original source ↗ Open in workspace

recordType

paper

region

Global