Risk-Aware Algorithms for Adversarial Contextual Bandits
This addresses risk management in sequential decision-making for applications like finance or robotics, though it is incremental as it extends existing bandit frameworks with constraints.
The paper tackles adversarial contextual bandits with risk constraints by developing algorithms that minimize cumulative cost while ensuring long-term risk constraints are met, achieving near-optimal regret and sublinear risk violation growth.
In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then receives the corresponding cost and risk associated with the pulled arm. In addition to minimizing the cumulative cost, the learner also needs to satisfy long-term risk constraints -- the average of the cumulative risk from all pulled arms should not be larger than a pre-defined threshold. To address this problem, we first study the full information setting where in each round the learner receives an adversarial convex loss and a convex constraint. We develop a meta algorithm leveraging online mirror descent for the full information setting and extend it to contextual bandit with risk constraints setting using expert advice. Our algorithms can achieve near-optimal regret in terms of minimizing the total cost, while successfully maintaining a sublinear growth of cumulative risk constraint violation.