On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring

TL;DR

This paper investigates the sample complexity of multi-agent decision-making, establishing bounds and revealing fundamental differences from single-agent scenarios, especially regarding hidden rewards and partial monitoring.

Contribution

It introduces a multi-agent generalization of the Decision-Estimation Coefficient, analyzes the complexity gaps, and connects multi-agent complexity to hidden-reward single-agent problems.

Findings

Upper and lower bounds on sample complexity for multi-agent decision making.

Multi-agent complexity bounds have inherent gaps not closed by reasonable measures.

Conditions identified where multi-agent complexity reduces to single-agent complexity.

Abstract

A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move from few to many agents. We study this question in a general framework for interactive decision making with multiple agents, encompassing Markov games with function approximation and normal-form games with bandit feedback. We focus on equilibrium computation, in which a centralized learning algorithm aims to compute an equilibrium by controlling multiple agents that interact with an unknown environment. Our main contributions are: - We provide upper and lower bounds on the optimal sample complexity for multi-agent decision making based on a multi-agent generalization of the Decision-Estimation Coefficient, a complexity measure introduced by Foster et al. (2021) in the single-agent counterpart to our setting. Compared to the best results for the single-agent setting, our bounds have additional gaps. We show that no "reasonable" complexity measure can close these gaps, highlighting a striking separation between single and multiple agents. - We show that characterizing the statistical complexity for multi-agent decision making is equivalent to characterizing the statistical complexity of single-agent decision making, but with hidden (unobserved) rewards, a framework that subsumes variants of the partial monitoring problem. As a consequence, we characterize the statistical complexity for hidden-reward interactive decision making to the best extent possible. Building on this development, we provide several new structural results, including 1) conditions under which the statistical complexity of multi-agent decision making can be reduced to that of single-agent, and 2) conditions under which the so-called curse of multiple agents can be avoided.