SHF: Small: High-Performance Multi-Agent Reinforcement Learning

SHF：小型：高性能多智能体强化学习

基本信息

批准号：
2114415
负责人：
Guru Prasadh Venkataramani
金额：
$ 49.98万
依托单位：
George Washington University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2021
资助国家：
美国
起止时间：
2021-10-01 至 2024-09-30
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2114415&HistoricalAwards=false
关键词：
SHF Small Performance Multi Agent

项目摘要

Artificial Intelligence (AI) has rapidly become a critical domain with applications in autonomous driving, robotics, aerospace, healthcare, and others. For a machine (AI agent) to closely mimic human behavior and operate effectively, it should possess the capabilities of robust decision making and learning simultaneously as it operates in the environment. Multi-Agent Reinforcement Learning (MARL) is a promising research area that can model and control multiple distributed decision-making AI agents. However, recent studies have shown that the MARL algorithms suffer from inefficiencies that can severely limit their adoption in real-world systems. These problems occur due to complexities in decision-making processes arising from having to observe and act upon a large number of events present in the environment, along with the growth in the number of AI agents needed to interact with each other.To ameliorate the learning efficiency and scalability issues of MARL algorithms, the project investigators adopt a novel interdisciplinary solution approach, harnessing computer architecture, machine-learning theory and optimization. Specifically, the project will seek techniques to improve neural-network throughput, to efficiently manage the state-action space in a dynamic fashion and to scalably encode states and observations of a large and varying number of agents. A hardware-software co-design approach is adopted to accelerate the concurrent optimization of software and hardware layers. The research outcomes of this project will significantly enhance the adoption of MARL frameworks in real-world applications and positively impact university curricular development and the computing industry.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人工智能 (AI) 已迅速成为自动驾驶、机器人、航空航天、医疗保健等领域应用的关键领域。对于机器（人工智能代理）来说，要紧密模仿人类行为并有效运行，它应该在环境中运行时具备稳健的决策和学习能力。多智能体强化学习（MARL）是一个有前景的研究领域，可以建模和控制多个分布式决策人工智能智能体。然而，最近的研究表明，MARL 算法效率低下，严重限制了它们在现实系统中的采用。这些问题的出现是由于必须观察环境中存在的大量事件并采取行动而导致决策过程变得复杂，以及相互交互所需的人工智能代理数量的增长。针对 MARL 算法的效率和可扩展性问题，项目研究人员采用了一种新颖的跨学科解决方法，利用计算机架构、机器学习理论和优化。具体来说，该项目将寻求提高神经网络吞吐量的技术，以动态方式有效管理状态动作空间，并可扩展地编码大量不同数量代理的状态和观察。采用软硬件协同设计的方式，加速软硬件层的并行优化。该项目的研究成果将显着提高 MARL 框架在实际应用中的采用，并对大学课程开发和计算机行业产生积极影响。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值进行评估，认为值得支持以及更广泛的影响审查标准。

项目成果

期刊论文数量（5）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Scalability Bottlenecks in Multi-Agent Reinforcement Learning Systems

DOI：
10.48550/arxiv.2302.05007
发表时间：
2023-02
期刊：
ArXiv
影响因子：
0
作者：
Kailash Gogineni;Peng Wei;Tian Lan;Guru Venkataramani
通讯作者：
Kailash Gogineni;Peng Wei;Tian Lan;Guru Venkataramani

MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization

DOI：
10.48550/arxiv.2302.10418
发表时间：
2023-02
期刊：
ArXiv
影响因子：
0
作者：
Yongsheng Mei;Hanhan Zhou;Tian Lan;Guru Venkataramani;Peng Wei
通讯作者：
Yongsheng Mei;Hanhan Zhou;Tian Lan;Guru Venkataramani;Peng Wei

AccMER: Accelerating Multi-Agent Experience Replay with Cache Locality-Aware Prioritization

DOI：
10.1109/asap57973.2023.00041
发表时间：
2023-05
期刊：
2023 IEEE 34th International Conference on Application-specific Systems, Architectures and Processors (ASAP)
影响因子：
0
作者：
Kailash Gogineni;Yongsheng Mei;Peng Wei;Tian Lan;Guru Venkataramani
通讯作者：
Kailash Gogineni;Yongsheng Mei;Peng Wei;Tian Lan;Guru Venkataramani

Towards Efficient Multi-Agent Learning Systems