On Uncertainty and Robustness in Large-Scale Intelligent Data Fusion Systems

Marlin, Benjamin M.; Abdelzaher, Tarek; Ciocarlie, Gabriela F.; Cobb, Adam D.; Dennison, Mark; Jalaian, Brian; Kaplan, Lance; Raber, Tiffany; Raglin, Adrienne; Sharma, Piyush; Srivastava, Mani; Trout, Theron; Vadera, Meet P.; Wigness, Maggie

doi:10.1109/cogmi50398.2020.00020

Cited by 8 publications

(1 citation statement)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Limited access to real-world data and an inability to meet state-of-the-art infrastructure requirement to process massive amount of information generated by RL algorithms may not only leave coalition partners vulnerable to adversarial attack, but also introduce uncertainties (data, model, platform, etc.) 21,27 Distributed learning is commonly used in MARL to study the coordination among agents trying to solve an environmental task. [28][29][30] Proposed CLDE can be seen as a possible option to address scalability issue in complex military settings where mission success relies on rapidly-adaptable teams of autonomous AI systems that interact and learn from human understanding of high-level mission goals.…”

Section: Marl Applications In Mdomentioning

confidence: 99%

Survey of recent multi-agent reinforcement learning algorithms utilizing centralized training

Sharma¹,

Fernández²,

Zaroukian³

et al. 2021

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III

Self Cite

View full text Add to dashboard Cite

Much work has been dedicated to the exploration of Multi-Agent Reinforcement Learning (MARL) paradigms implementing a centralized learning with decentralized execution (CLDE) approach to achieve human-like collab-oration in cooperative tasks. Here, we discuss variations of centralized training and describe a recent survey of algorithmic approaches. The goal is to explore how different implementations of information sharing mechanism in centralized learning may give rise to distinct group coordinated behaviors in multi-agent systems performing cooperative tasks.

show abstract

Section: Marl Applications In Mdomentioning

confidence: 99%

Survey of recent multi-agent reinforcement learning algorithms utilizing centralized training

Sharma¹,

Fernández²,

Zaroukian³

et al. 2021

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III

Self Cite

View full text Add to dashboard Cite

show abstract

The United States Department of Energy and National Institutes of Health Collaboration: Medical Care Advances by Discovery in Radiation Detection

Buchsbaum,

Capala,

Obcemea

et al. 2024

Medical Physics

View full text Add to dashboard Cite

A National Institutes of Health (NIH) and U.S. Department of Energy (DOE) Office of Science virtual workshop on shared general topics was held in July of 2021 and reported on in this publication in January of 2023. Following the inaugural 2021 joint meeting representatives from the DOE Office of Science and NIH met to discuss organizing a second joint workshop that would concentrate on radiation detection to bring together teams from both agencies and their grantee populations to stimulate collaboration and efficiency. To meet this scientific mission within the NIH and DOE radiation detection space, the organizers assembled workshop sessions covering the state‐of‐the‐art in cameras, detectors, and sensors for radiation external and internal (diagnostic and therapeutic) to human, data acquisition and electronics, image reconstruction and processing, and the application of artificial intelligence. NIH and DOE are committed to continuing the process of convening a joint workshop every 12–24 months. This Special Report recaps the findings of this second workshop. Beyond showing only the innovations and areas of success, important gaps in our knowledge were defined and presented. We summarize by defining four areas of greatest opportunity and need that emerged from the unique, dynamic dialogue the in‐person workshop provided the attendees.

show abstract