Organizations often pool dispersed information into one ranking and then allow many agents to act on that shared view. In a discovery problem, this can improve beliefs while reducing coverage.
arXiv:2607. 18045v1 Announce Type: new Abstract: Organizations often pool dispersed information into one ranking and then allow many agents to act on that shared view.
The paper investigates when information sharing enhances decentralized discovery by separating its effects on pooled estimation and independent rescue actions in finite discovery models. It shows that a registered incremental-sharing protocol improves discovery only when pooled residual error decreases faster than an independent rescue attempt, and that equilibrium selection can determine whether sharing is beneficial. The study uses synthetic, finite models without human or organizational data.
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.
arXiv:2609.22757v1 Announce Type: cross Abstract: A (coarse) correlated equilibrium (CE) is information-value-free (IVF) if a player can match the payoff obtained from recommendations by committing t...
arXiv:2602. 16965v2 Announce Type: replace Abstract: We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward.
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:2606. 29457v1 Announce Type: new Abstract: When two companies bid to buy the same target, no one knows exactly what the target is worth.
arXiv:2608. 12831v1 Announce Type: cross Abstract: Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model agents---while each reward-bearing interaction can be costly or risky.
The paper investigates the problem of sharing a single critic across multiple parallel environments in reinforcement learning. It shows that when environments assign different expected returns to the same state, a shared critic must reconcile conflicting value targets, which can distort advantage estimates and misguide policy updates. The authors propose a simple fix—providing the critic with the environment index—demonstrating through bandit models and experiments on CartPole, MuJoCo, BipedalWalker, and 16 Procgen games that this conditional critic stabilizes learning and boosts returns, achieving a 40.8% improvement in aggregate normalized return on unseen levels.
arXiv:2609.06816v1 Announce Type: new Abstract: Decision-time search in perfect and imperfect information games with enumerable belief states are effective methods for game AI. Collectible card games...
arXiv:2603. 13356v2 Announce Type: replace Abstract: Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget.
arXiv:2608. 11560v1 Announce Type: new Abstract: Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a downstream conversion - is observed only weeks later, too late to drive online learning.