# Contextual Combinatorial Conservative Bandits

arXiv: https://arxiv.org/abs/1911.11337 · HTML: https://mlsanity.com/paper/1911.11337/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 4 of 4)

- [A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning](https://mlsanity.com/paper/2106.11692/) (2021)
- [Conservative Contextual Combinatorial Cascading Bandit](https://mlsanity.com/paper/2104.08615/) (2021)
- [Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation](https://mlsanity.com/paper/2312.15458/) (2023)
- [Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines](https://mlsanity.com/paper/2609.39106/) (2026)

## Abstract (arXiv)

The problem of multi-armed bandits (MAB) asks to make sequential decisions while balancing between exploitation and exploration, and have been successfully applied to a wide range of practical scenarios. Various algorithms have been designed to achieve a high reward in a long term. However, its short-term performance might be rather low, which is injurious in risk sensitive applications. Building on previous work of conservative bandits, we bring up a framework of contextual combinatorial conservative bandits. An algorithm is presented and a regret bound of tilde O(d2+d√T) is proven, where d is the dimension of the feature vectors, and T is the total number of time steps. We further provide an algorithm as well as regret analysis for the case when the conservative reward is unknown. Experiments are conducted, and the results validate the effectiveness of our algorithm.