Hierarchical Coordination Multi-Agent Reinforcement Learning With Spatio-Temporal Abstraction

Ma, Tinghuai; Peng, Kexing; Rong, Huan; Qian, Yurong; Al-Nabhan, Najla

doi:10.1109/tetci.2023.3309738

IEEE Trans. Emerg. Top. Comput. Intell.

2024

DOI: 10.1109/tetci.2023.3309738

|View full text |Cite

Hierarchical Coordination Multi-Agent Reinforcement Learning With Spatio-Temporal Abstraction

Tinghuai Ma,

Kexing Peng,

Huan Rong

et al.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Hierarchical RNNs with graph policy and attention for drone swarm

Wei,

Cui,

Huang

et al. 2024

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

In recent years, the drone swarm has experienced remarkable growth, finding applications across diverse domains such as agricultural surveying, disaster rescue, and logistics delivery. However, the rapid expansion of drone swarm usage underscores the necessity for innovative approaches in the field. Traditional algorithms face challenges in adapting to complex tasks, environmental modeling, and computational complexity, highlighting the need for more advanced solutions like multi-agent deep reinforcement learning to enhance efficiency and robustness in drone swarm. Our proposed approach tackles this challenge by embracing temporal and spatial. In terms of the temporal, the proposed approach builds upon historical data, it enhances the predictive capabilities regarding future behaviors. In the spatial, the proposed approach leverage graph theory to model the swarm's features, while attention mechanisms strengthen the relationships between individual drones. The proposed approach addresses the unique characteristics of drone swarms by incorporating temporal dependencies, spatial structures, and attention mechanisms. Extensive experiments validate the effectiveness of the proposed approach.

show abstract

Hierarchical RNNs with graph policy and attention for drone swarm

Wei,

Cui,

Huang

et al. 2024

Journal of Computational Design and Engineering

View full text Add to dashboard Cite

show abstract

Target-Oriented Multi-Agent Coordination with Hierarchical Reinforcement Learning

Yu,

Zhai,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In target-oriented multi-agent tasks, agents collaboratively achieve goals defined by specific objects, or targets, in their environment. The key to success is the effective coordination between agents and these targets, especially in dynamic environments where targets may shift. Agents must adeptly adjust to these changes and re-evaluate their target interactions. Inefficient coordination can lead to resource waste, extended task times, and lower overall performance. Addressing this challenge, we introduce the regulatory hierarchical multi-agent coordination (RHMC), a hierarchical reinforcement learning approach. RHMC divides the coordination task into two levels: a high-level policy, assigning targets based on environmental state, and a low-level policy, executing basic actions guided by individual target assignments and observations. Stabilizing RHMC’s high-level policy is crucial for effective learning. This stability is achieved by reward regularization, reducing reliance on the dynamic low-level policy. Such regularization ensures the high-level policy remains focused on broad coordination, not overly dependent on specific agent actions. By minimizing low-level policy dependence, RHMC adapts more seamlessly to environmental changes, boosting learning efficiency. Testing demonstrates RHMC’s superiority over existing methods in global reward and learning efficiency, highlighting its effectiveness in multi-agent coordination.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Hierarchical Coordination Multi-Agent Reinforcement Learning With Spatio-Temporal Abstraction

Cited by 2 publications

References 20 publications

Hierarchical RNNs with graph policy and attention for drone swarm

Hierarchical RNNs with graph policy and attention for drone swarm

Target-Oriented Multi-Agent Coordination with Hierarchical Reinforcement Learning

Contact Info

Product

Resources

About