Distributed No-Regret Learning in Multi-Agent Systems

Abstract

In this tutorial article, we give an overview of new challenges and representative results on distributed no-regret learning in multi-agent systems modeled as repeated unknown games. Four emerging game characteristics---dynamicity, incomplete and imperfect feedback, bounded rationality, and heterogeneity---that challenge canonical game models are explored. For each of the four characteristics, we illuminate its implications and ramifications in game modeling, notions of regret, feasible game outcomes, and the design and analysis of distributed learning algorithms.

arXiv commentAccepted for publication in IEEE Signal Processing Magazine

References in corpus (7)

• Distributed Learning in Multi-Armed Bandit with Multiple Players
• Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret
• Adversarial Attacks on Stochastic Bandits
• No-regret Dynamics and Fictitious Play
• Bandit learning in concave $N$-person games
• Multi-agent online learning in time-varying games
• Policy Regret in Repeated Games