← Back to all news
arXiv Machine Learning By Michael Tang, Mahmoud Abdelgalil, Jorge I. Poveda

The Deceptive Bandit Problem: Exploratory Coupling and the Fragility of Multi-Agent Learning

Read the original on arXiv Machine Learning →

The paper investigates how randomized exploration in bandit learning can be compromised when an adversarial agent gains access to another agent’s exploratory signals. In a two‑player strongly monotone setting, the deceptive agent couples its actions with the leaked information to steer the learning dynamics toward a new steady state, termed the deceptive Nash equilibrium (DNE). The authors prove that the deceptive bandit learning dynamics converge to an arbitrarily small neighborhood of the DNE while maintaining optimal convergence rates, even under relaxed smoothness assumptions, and illustrate the impact on costs in a resource‑allocation game.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 8

Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards

The paper introduces a new class of offline adversarial attacks on warm‑start bandit algorithms with bounded rewards. Unlike prior methods that suppress non‑target arms, the authors show that promoting the target arm is essential when it lies near the lower reward boundary, and they design an attack that achieves optimal sublinear cost by balancing target promotion and non‑target suppression. The attack is extended to several popular bandit algorithms and validated experimentally on real‑world and synthetic data.

By Qirun Zeng, Manhin Poon, Xiangxiang Dai, Qixin Zhang, Jinhang Zuo
reinforcement-learningroboticssafety
More like this →
arXiv Machine Learning
3d ago

Characterizing Oblivious Common-Reward Multi-Player Bandits: Universal Stationarity, Coordination Traps, and Certified Global Rates

The paper analyzes the oblivious common-reward multi-player multi-armed bandit (OC-MPMAB), where players act independently without observing others and only share a common reward. It shows that the players’ gradient-bandit updates form an unbiased estimator of a hidden product-policy objective, guaranteeing universal finite‑time first‑order stationarity. The work also identifies conditions under which global optimality cannot be achieved, introduces certificates to recover global optimality under structural assumptions, and establishes corresponding product‑policy gap and pseudo‑regret bounds.

By Mingxiao Li, Wenhai Lai, Hongyu Wang
reinforcement-learning
More like this →