Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Jie, Zhang, Yinmin, Li, Chuming, Yang, Chao, Yang, Yaodong, Liu, Yu, Ouyang, Wanli
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2310.11846
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917595899232256
author Liu, Jie
Zhang, Yinmin
Li, Chuming
Yang, Chao
Yang, Yaodong
Liu, Yu
Ouyang, Wanli
author_facet Liu, Jie
Zhang, Yinmin
Li, Chuming
Yang, Chao
Yang, Yaodong
Liu, Yu
Ouyang, Wanli
contents Building a single generalist agent with strong zero-shot capability has recently sparked significant advancements. However, extending this capability to multi-agent decision making scenarios presents challenges. Most current works struggle with zero-shot transfer, due to two challenges particular to the multi-agent settings: (a) a mismatch between centralized training and decentralized execution; and (b) difficulties in creating generalizable representations across diverse tasks due to varying agent numbers and action spaces. To overcome these challenges, we propose a Mask-Based collaborative learning framework for Multi-Agent decision making (MaskMA). Firstly, we propose to randomly mask part of the units and collaboratively learn the policies of unmasked units to handle the mismatch. In addition, MaskMA integrates a generalizable action representation by dividing the action space into intrinsic actions solely related to the unit itself and interactive actions involving interactions with other units. This flexibility allows MaskMA to tackle tasks with varying agent numbers and thus different action spaces. Extensive experiments in SMAC reveal MaskMA, with a single model trained on 11 training maps, can achieve an impressive 77.8% average zero-shot win rate on 60 unseen test maps by decentralized execution, while also performing effectively on other types of downstream tasks (e.g., varied policies collaboration, ally malfunction, and ad hoc team play).
format Preprint
id arxiv_https___arxiv_org_abs_2310_11846
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning
Liu, Jie
Zhang, Yinmin
Li, Chuming
Yang, Chao
Yang, Yaodong
Liu, Yu
Ouyang, Wanli
Artificial Intelligence
Building a single generalist agent with strong zero-shot capability has recently sparked significant advancements. However, extending this capability to multi-agent decision making scenarios presents challenges. Most current works struggle with zero-shot transfer, due to two challenges particular to the multi-agent settings: (a) a mismatch between centralized training and decentralized execution; and (b) difficulties in creating generalizable representations across diverse tasks due to varying agent numbers and action spaces. To overcome these challenges, we propose a Mask-Based collaborative learning framework for Multi-Agent decision making (MaskMA). Firstly, we propose to randomly mask part of the units and collaboratively learn the policies of unmasked units to handle the mismatch. In addition, MaskMA integrates a generalizable action representation by dividing the action space into intrinsic actions solely related to the unit itself and interactive actions involving interactions with other units. This flexibility allows MaskMA to tackle tasks with varying agent numbers and thus different action spaces. Extensive experiments in SMAC reveal MaskMA, with a single model trained on 11 training maps, can achieve an impressive 77.8% average zero-shot win rate on 60 unseen test maps by decentralized execution, while also performing effectively on other types of downstream tasks (e.g., varied policies collaboration, ally malfunction, and ad hoc team play).
title MaskMA: Towards Zero-Shot Multi-Agent Decision Making with Mask-Based Collaborative Learning
topic Artificial Intelligence
url https://arxiv.org/abs/2310.11846