Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bettini, Matteo, Kortvelesy, Ryan, Prorok, Amanda
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917673962569728
author Bettini, Matteo
Kortvelesy, Ryan
Prorok, Amanda
author_facet Bettini, Matteo
Kortvelesy, Ryan
Prorok, Amanda
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15054
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
Bettini, Matteo
Kortvelesy, Ryan
Prorok, Amanda
Multiagent Systems
Artificial Intelligence
Machine Learning
Robotics
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.
title Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
topic Multiagent Systems
Artificial Intelligence
Machine Learning
Robotics
url https://arxiv.org/abs/2405.15054