Measurement Maximizing Adaptive Sampling with Risk Bounding Functions

Authors: Benjamin Ayton, Brian Williams, Richard Camilli7511-7519

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Through experiments on real bathymetric data and simulated measurements, we show our algorithm allows an agent to take dangerous actions only when the reward justifies the risk. We then verify through Monte Carlo simulations that failure bounds are satisfied.
Researcher Affiliation Collaboration Benjamin Ayton, Brian Williams Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology {aytonb, williams}@mit.edu Richard Camilli Woods Hole Oceanographic Institute rcamilli@whoi.edu
Pseudocode Yes Algorithm 1: Execute Risk Bounded Policy; Algorithm 2: Sample
Open Source Code No The paper does not include an unambiguous statement that the authors are releasing the code for the work described in this paper, nor does it provide a direct link to a source-code repository for their methodology.
Open Datasets Yes The location was East of Boston Harbor, from -70.890 to -70.876 degrees longitude, and 42.344 to 42.355 degrees latitude, provided by NOAA survey H10992 (National Oceanic and Atmospheric Administration 2001).
Dataset Splits No The paper mentions "Monte Carlo simulations" and using "real bathymetric data" but does not specify explicit training, validation, or test dataset splits with percentages or sample counts.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup Yes We used the following parameters: n = 20, τ = 60 sec, Σ0 = 0I m2, Σw = 12I m2, Rmin = 12.5, lmin = 12.5 m, m(x) = 16, k(x, x ) = 1.25 exp x x 2 /(2 (200 m)2) , σ = 0. ... The following parameters were changed: n = 8, τ = 2 sec, Σw = 60I m2, lmin = 25 m. The distance traveled by every action was changed to 100 m.