AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Improving Surveillance Using Cooperative Target Observation

Rashi Aswani, Sai Krishna Munnangi, Praveen Paruchuri

AAAI 2017 · Multi-agent systems and games › Games and equilibria · approach: Cooperation and social dilemmas

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
set alpha to 1 instead of 0.25 or small values (ablation)k-means style observer · 18 observers, 3/9/15 targetsavg targets observed: 4.39 -> 6.82Improved
use 0-1 weight model instead of 0-.5-1 model (ablation)Explore-Exploit observer · 10 observers, 3-27 targetsmean targets observed: 1.76 -> 2.3 (3 targets); 10.9 -> 11.47 (27 targets)Improved
0-1 model versus Model 3 (ablation)Explore-Exploit observer · 10 observers, 3-27 targetsmean targets observed: 2.21 -> 2.3Improved
target controlled randomization mix 70-30 versus 50-50 (ablation)target strategy · 10 observers, 27 targetsmean targets observed (lower better for targets): 11.93 -> 11.62Improved
targets use straight-line movement instead of randomtargets · sensor 15, speeds 0.5-1.2targets observedImproved
controlled randomization instead of purely random target movementtargets · sensor 15, speeds 0.5-1.2targets observedImproved
add randomness to straight-line target movementtargets · sensor 15targets observedHurt
memorization observer versus Explore-ExploitExplore-Exploit · controlled randomization targetstargets observedMixed
one-step prediction versus Explore-ExploitExplore-Exploit · controlled randomization targetstargets observedNo clear effect
k-step prediction versus Explore-ExploitExplore-Exploit · controlled randomization targetstargets observedImproved
raise reward threshold in BRLP-CTO from 50% to 100% of optimal (ablation)BRLP-CTO · sensor 15, speeds 0.8/1.2average entropy: 3.321 -> 2.137Hurt

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