Multiagent Online Learning in Dynamic and Uncertain Environments
Abstract
Multiagent online learning studies how multiple decision-making agents adapt their behavior over time in response to strategic interaction, uncertainty, and nonstationary environments created by other adaptive agents. Such settings arise naturally in large-scale engineered and sociotechnical systems, including transportation networks, energy markets, financial systems, supply chains, and emerging agentic artificial intelligence platforms, where agents may be any combination of humans, algorithms, and physical systems. This article presents a tutorial overview of learning in games and evolutionary game theory as a foundational framework for modeling and analyzing these interactions. We introduce core game-theoretic concepts and discuss how these outcomes may emerge under adaptive learning dynamics, along with selected impossibility results that capture obstacles to these outcomes. Representative discrete-time and continuous-time learning algorithms and their connections are reviewed alongside their convergence and long-run properties. The tutorial further presents learning for stochastic and Markov game settings, drawing connections to multiagent reinforcement learning and illustrating how strategic-form learning results can be leveraged in this generalized setting.
Funding: C. Eksin acknowledges support from NSF CAREER 2239410, ONR 23-000004885, and NSF 2533864. B. Touri is supported by AFOSR FA9550-24-1-0129.
Supplemental Material: The supplemental appendix is available at https://doi.org/10.1287/educ.2026.0302.
Your Access Options
-
Login Options
Purchase Options
Save for laterOther Options
Token AccessClaim access using a tokenRestore guest accessApplies for purchases made as a guest
