AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Measurement Maximizing Adaptive Sampling with Risk Bounding Functions

Benjamin Ayton, Brian Williams, Richard Camilli

AAAI 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Tree search and policy optimization · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add extra obstacles to the North and East and raise vehicle covariance (Sigma_w 60I -> 100I) so danger exists in all directionsrisk-bounded MCTS adaptive sampling · Monte Carlo failure-rate testfraction of permitted risk used: 32% -> 63%Improved
Use a lower risk bounding function Delta(x)=0.0002x instead of 0.0003xrisk-bounded MCTS adaptive sampling · Boston Harbor bathymetry simulationtrajectory behaviorMixed
Use a very strict risk bounding function Delta(x)=0.0001xrisk-bounded MCTS adaptive sampling · Boston Harbor bathymetry simulationtrajectory behaviorHurt
Use the looser risk bounding function Delta(x)=0.0003xrisk-bounded MCTS adaptive sampling · Boston Harbor bathymetry simulationtrajectory behaviorImproved
Apply risk bounding function Delta(x)=0.001x over 10,000 random GP instancesrisk-bounded MCTS adaptive sampling · Monte Carlo failure-rate testmeasured failure rate vs permitted: 0.0649 -> 0.0208Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy