The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability

TL;DR

This paper introduces a sample-efficient online learning algorithm that addresses the challenges of information asymmetry and knowledge transfer in strategic multi-agent environments, achieving near-optimal policy learning.

Contribution

It presents a novel algorithm that effectively learns system dynamics under information asymmetry and knowledge transfer challenges with proven sample complexity bounds.

Findings

Achieves $ ext{O}(1/ ext{epsilon}^2)$ sample complexity for $ ext{epsilon}$-optimal policy

Handles non-i.i.d. actions in confounder learning

Addresses knowledge transfer in strategic online learning environments

Abstract

Information asymmetry is a pervasive feature of multi-agent systems, especially evident in economics and social sciences. In these settings, agents tailor their actions based on private information to maximize their rewards. These strategic behaviors often introduce complexities due to confounding variables. Simultaneously, knowledge transportability poses another significant challenge, arising from the difficulties of conducting experiments in target environments. It requires transferring knowledge from environments where empirical data is more readily available. Against these backdrops, this paper explores a fundamental question in online learning: Can we employ non-i.i.d. actions to learn about confounders even when requiring knowledge transfer? We present a sample-efficient algorithm designed to accurately identify system dynamics under information asymmetry and to navigate the challenges of knowledge transfer effectively in reinforcement learning, framed within an online strategic interaction model. Our method provably achieves learning of an $\epsilon$-optimal policy with a tight sample complexity of $O(1/\epsilon^2)$.