COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents

TL;DR

This paper introduces COBRA, a novel algorithm for contextual bandit problems with strategic agents, ensuring truthful reporting without monetary incentives, and providing incentive compatibility and sub-linear regret guarantees.

Contribution

We propose COBRA, a new algorithm that incentivizes truthful reporting from strategic agents in contextual bandits without monetary rewards, with proven theoretical guarantees.

Findings

COBRA achieves incentive compatibility with strategic agents.

The algorithm guarantees sub-linear regret in the presence of strategic behavior.

Experimental results validate the effectiveness of COBRA in practical scenarios.

Abstract

This paper considers a contextual bandit problem involving multiple agents, where a learner sequentially observes the contexts and the agent's reported arms, and then selects the arm that maximizes the system's overall reward. Existing work in contextual bandits assumes that agents truthfully report their arms, which is unrealistic in many real-life applications. For instance, consider an online platform with multiple sellers; some sellers may misrepresent product quality to gain an advantage, such as having the platform preferentially recommend their products to online users. To address this challenge, we propose an algorithm, COBRA, for contextual bandit problems involving strategic agents that disincentivize their strategic behavior without using any monetary incentives, while having incentive compatibility and a sub-linear regret guarantee. Our experimental results also validate the different performance aspects of our proposed algorithm.