Publications (5)
Provenance-Based Interpretation of Multi-Agent Information Analysis
Scott Friedman, Jeff Rye, David LaVergne +3
Analytic software tools and workflows are increasing in capability, complexity, number, and scale, and the integrity of our workflows is as important as ever. Specifically, we must…
A Scalable Finite Difference Method for Deep Reinforcement Learning
Matthew Allen, John Raisbeck, Hakho Lee
Several low-bandwidth distributable black-box optimization algorithms in the family of finite differences such as Evolution Strategies have recently been shown to perform nearly as…
H-ATLAS/GAMA: Quantifying the Morphological Evolution of the Galaxy Population Using Cosmic Calorimetry
Stephen Eales, Andrew Fullard, Matthew Allen +28
Using results from the Herschel Astrophysical Terrahertz Large-Area Survey and the Galaxy and Mass Assembly project, we show that, for galaxy masses above approximately 1.0e8 solar…
Collaborative Drill Alignment in Surgical Robotics
Daniel Larby, Joshua Kershaw, Matthew Allen +1
Robotic assistance allows surgeries to be reliably and accurately executed while still under direct supervision of the surgeon, combining the strengths of robotic technology with t…
Evolution Strategies Converges to Finite Differences
John C. Raisbeck, Matthew Allen, Ralph Weissleder +2
Since the debut of Evolution Strategies (ES) as a tool for Reinforcement Learning by Salimans et al. 2017, there has been interest in determining the exact relationship between the…