Scaling up cooperative multi-agent reinforcement learning systems

Cooperative multi-agent reinforcement learning methods aim to learn effective collaborative behaviours of multiple agents performing complex tasks. However, existing MARL methods are commonly proposed for fairly small-scale multi-agent benchmark problems, wherein both the number of agents and the le...

Full description

Saved in:
Bibliographic Details
Main Author: GENG, Minghong
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9750
https://ink.library.smu.edu.sg/context/sis_research/article/10750/viewcontent/p2737__1_.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10750
record_format dspace
spelling sg-smu-ink.sis_research-107502024-12-16T03:21:23Z Scaling up cooperative multi-agent reinforcement learning systems GENG, Minghong Cooperative multi-agent reinforcement learning methods aim to learn effective collaborative behaviours of multiple agents performing complex tasks. However, existing MARL methods are commonly proposed for fairly small-scale multi-agent benchmark problems, wherein both the number of agents and the length of the time horizons are typically restricted. My initial work investigates hierarchical controls of multi-agent systems, where a unified overarching framework coordinates multiple smaller multi-agent subsystems, tackling complex, long-horizon tasks that involve multiple objectives. Addressing another critical need in the field, my research introduces a comprehensive benchmark for evaluating MARL methods in long-horizon, multi-agent, and multi-objective scenarios. This benchmark aims to fill the current gap in the MARL community for assessing methodologies in more complex and realistic scenarios. My dissertation would focus on proposing and evaluating methods for scaling up multi-agent systems in two aspects: structural-wise increasing the number of reinforcement learning agents and temporal-wise extending the planning horizon and complexity of problem domains that agents are deployed in. 2024-05-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9750 https://ink.library.smu.edu.sg/context/sis_research/article/10750/viewcontent/p2737__1_.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Multi-agent Reinforcement Learning Scaling up MARL Long-horizon MARL Hierarchical Multi-agent Systems Task Decomposition Multi-agent learning Reinforcement learning Scalability Collective learning Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Multi-agent Reinforcement Learning
Scaling up MARL
Long-horizon MARL
Hierarchical Multi-agent Systems
Task Decomposition
Multi-agent learning
Reinforcement learning
Scalability
Collective learning
Databases and Information Systems
spellingShingle Multi-agent Reinforcement Learning
Scaling up MARL
Long-horizon MARL
Hierarchical Multi-agent Systems
Task Decomposition
Multi-agent learning
Reinforcement learning
Scalability
Collective learning
Databases and Information Systems
GENG, Minghong
Scaling up cooperative multi-agent reinforcement learning systems
description Cooperative multi-agent reinforcement learning methods aim to learn effective collaborative behaviours of multiple agents performing complex tasks. However, existing MARL methods are commonly proposed for fairly small-scale multi-agent benchmark problems, wherein both the number of agents and the length of the time horizons are typically restricted. My initial work investigates hierarchical controls of multi-agent systems, where a unified overarching framework coordinates multiple smaller multi-agent subsystems, tackling complex, long-horizon tasks that involve multiple objectives. Addressing another critical need in the field, my research introduces a comprehensive benchmark for evaluating MARL methods in long-horizon, multi-agent, and multi-objective scenarios. This benchmark aims to fill the current gap in the MARL community for assessing methodologies in more complex and realistic scenarios. My dissertation would focus on proposing and evaluating methods for scaling up multi-agent systems in two aspects: structural-wise increasing the number of reinforcement learning agents and temporal-wise extending the planning horizon and complexity of problem domains that agents are deployed in.
format text
author GENG, Minghong
author_facet GENG, Minghong
author_sort GENG, Minghong
title Scaling up cooperative multi-agent reinforcement learning systems
title_short Scaling up cooperative multi-agent reinforcement learning systems
title_full Scaling up cooperative multi-agent reinforcement learning systems
title_fullStr Scaling up cooperative multi-agent reinforcement learning systems
title_full_unstemmed Scaling up cooperative multi-agent reinforcement learning systems
title_sort scaling up cooperative multi-agent reinforcement learning systems
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/9750
https://ink.library.smu.edu.sg/context/sis_research/article/10750/viewcontent/p2737__1_.pdf
_version_ 1819113127453655040