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

arXiv:2608.26755v1 Announce Type: new Abstract: 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 enforce safety by requiring the expected cost of each action to remain below a prescribed threshold. However, this may be insufficient in heteroscedastic settings, where the chosen action affects not only the expected reward and cost, but also the variability of the observed outcomes. We study contextual bandits with one-dimensional continuous actions and stage-wise high-probability constraints on the realized cost. We propose High-Probability Constrained UCB, an optimistic-pessimistic algorithm that explores for reward while conservatively estimating the safe action set. For linear reward and cost models, we prove a tight ilde{O}(dsqrt{T}) regret bound, and we extend the analysis to general function classes using the eluder dimension. Experiments show that enforcing realized-cost safety substantially reduces violations compared with expected-cost constrained baselines.

Related

• Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection
• Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees
• Pessimistic Risk-Aware Policy Learning in Contextual Bandits

Source: arXiv cs.LG | 2026-08-28