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.
arXiv:2608. 09389v1 Announce Type: cross Abstract: This note aims to serve as an entry point to the literature on learning in games, a topic with significant theoretical appeal and a wide range of applications -- from machine learning and data science to economics and beyond.
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.
arXiv:2607. 00155v1 Announce Type: new Abstract: We study runtime human oversight of an AI agent when private information runs in both directions: the human privately knows her reward function, while the AI privately knows the quality of the action it proposes.
arXiv:2609.13547v1 Announce Type: new Abstract: We study switching regret in adversarial multi-armed bandits, where the learner competes with an arm sequence that changes at most $S$ times. When $S$...
arXiv:2610.18899v1 Announce Type: cross Abstract: Thompson sampling (TS) achieves logarithmic and asymptotically optimal regret in classical stochastic bandits, but its behavior in multi-agent learni...
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.
arXiv:2608. 10529v1 Announce Type: cross Abstract: The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions.
The paper investigates how to infer agents’ underlying incentives in strategic multi‑agent settings, where traditional inverse reinforcement learning (IRL) may fail to produce rewards that guide optimal play. It introduces the concept of strategic identifiability and shows that learning from a fixed pair of policies can be insufficient regardless of sample size. To address this, the authors propose an active IRL algorithm for two‑player repeated Stackelberg games, combining maximum‑likelihood estimation with experimental design to achieve finite‑sample guarantees on sub‑optimality, and validate the approach in an anti‑poaching scenario.
arXiv:2606. 19883v1 Announce Type: new Abstract: We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model.
arXiv:2506. 03802v2 Announce Type: replace Abstract: We introduce a learning problem in a generalized two-sided matching market, where agents select actions to interact with their match.
arXiv:2608. 10526v1 Announce Type: cross Abstract: Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown.
arXiv:2608. 08268v1 Announce Type: cross Abstract: As firms increasingly deploy machine learning for strategic decision-making, understanding algorithmic interactions has become central to operations research and economics.