Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning

TL;DR

This paper introduces Diversity Control (DiCo), a novel method for precisely controlling behavioral diversity in Multi-Agent Reinforcement Learning without altering the learning objective, improving performance and sample efficiency.

Contribution

DiCo is a new approach that enforces exact diversity levels by architectural constraints, applicable to any actor-critic MARL algorithm, and is theoretically proven to achieve the desired diversity.

Findings

DiCo effectively controls diversity to a specified value.

Using DiCo improves performance in cooperative and competitive MARL tasks.

DiCo enhances sample efficiency in multi-agent learning environments.

Abstract

The study of behavioral diversity in Multi-Agent Reinforcement Learning (MARL) is a nascent yet promising field. In this context, the present work deals with the question of how to control the diversity of a multi-agent system. With no existing approaches to control diversity to a set value, current solutions focus on blindly promoting it via intrinsic rewards or additional loss functions, effectively changing the learning objective and lacking a principled measure for it. To address this, we introduce Diversity Control (DiCo), a method able to control diversity to an exact value of a given metric by representing policies as the sum of a parameter-shared component and dynamically scaled per-agent components. By applying constraints directly to the policy architecture, DiCo leaves the learning objective unchanged, enabling its applicability to any actor-critic MARL algorithm. We theoretically prove that DiCo achieves the desired diversity, and we provide several experiments, both in cooperative and competitive tasks, that show how DiCo can be employed as a novel paradigm to increase performance and sample efficiency in MARL. Multimedia results are available on the paper's website: https://sites.google.com/view/dico-marl.