Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fosong, Elliot, Rahman, Arrasy, Carlucho, Ignacio, Albrecht, Stefano V.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2302.04944
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914679324934144
author Fosong, Elliot
Rahman, Arrasy
Carlucho, Ignacio
Albrecht, Stefano V.
author_facet Fosong, Elliot
Rahman, Arrasy
Carlucho, Ignacio
Albrecht, Stefano V.
contents Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate efficient learning of complex multi-agent tasks, we propose an approach which uses an expert-provided decomposition of a task into simpler multi-agent sub-tasks. In each sub-task, a subset of the entire team is trained to acquire sub-task-specific policies. The sub-teams are then merged and transferred to the target task, where their policies are collectively fine-tuned to solve the more complex target task. We show empirically that such approaches can greatly reduce the number of timesteps required to solve a complex target task relative to training from-scratch. However, we also identify and investigate two problems with naive implementations of approaches based on sub-task decomposition, and propose a simple and scalable method to address these problems which augments existing actor-critic algorithms. We demonstrate the empirical benefits of our proposed method, enabling sub-task decomposition approaches to be deployed in diverse multi-agent tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2302_04944
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition
Fosong, Elliot
Rahman, Arrasy
Carlucho, Ignacio
Albrecht, Stefano V.
Multiagent Systems
Artificial Intelligence
Machine Learning
Training a team to complete a complex task via multi-agent reinforcement learning can be difficult due to challenges such as policy search in a large joint policy space, and non-stationarity caused by mutually adapting agents. To facilitate efficient learning of complex multi-agent tasks, we propose an approach which uses an expert-provided decomposition of a task into simpler multi-agent sub-tasks. In each sub-task, a subset of the entire team is trained to acquire sub-task-specific policies. The sub-teams are then merged and transferred to the target task, where their policies are collectively fine-tuned to solve the more complex target task. We show empirically that such approaches can greatly reduce the number of timesteps required to solve a complex target task relative to training from-scratch. However, we also identify and investigate two problems with naive implementations of approaches based on sub-task decomposition, and propose a simple and scalable method to address these problems which augments existing actor-critic algorithms. We demonstrate the empirical benefits of our proposed method, enabling sub-task decomposition approaches to be deployed in diverse multi-agent tasks.
title Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2302.04944