AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

EPOC: Efficient Perception via Optimal Communication

Masoumeh Heidari Kapourchali, Bonny Banerjee

AAAI 2020 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Learned inter-agent communication · 4 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
communicate with all agents instead of none (ablation)EPOC head agent · KARDaccuracy (%): 24.2±1 -> 88.1±1Improved
communicate with all agents instead of none (ablation)EPOC head agent · UTD-MHAD (Kinect skeleton)accuracy (%): 18.6±2 -> 73.1±4Improved
use learned communication policy instead of full communication (ablation)EPOC · KARDaccuracy (%): 88.1±1 -> 90.2±3Improved
use learned communication policy instead of full communication (ablation)EPOC · UTD-MHAD (Kinect skeleton)accuracy (%): 73.1±4 -> 80.1±4Improved
use learned communication policy instead of full communication (ablation)EPOC · UTD-MHAD multimodal (27 actions)accuracy (%): 84.6 -> 85.11Mixed
communicate with all agents instead of none (ablation)EPOC inertia agent · UTD-MHAD multimodal (27 actions)accuracy (%): 29.2 -> 84.6Improved
learned policy reduces communication to a fraction of test cases (ablation)EPOC · KARDcommunication rate (%): 63.54%Improved
learned policy reduces communication to a fraction of test cases (ablation)EPOC · UTD-MHAD (Kinect skeleton)communication rate (%): 61.32%Improved
online non-myopic decision-making instead of myopic offline Value of Information (ablation)EPOC · KARD/UTD-MHAD random failureaccuracyImproved
online updating of agents' models instead of non-adaptive (ablation)EPOC · KARD/UTD-MHAD persistent random messagesnumber of communicationsImproved
use ConvNets (60x10^6 params) instead of EPOC (67x10^3 params)comparison · UTD-MHAD multimodal (27 actions)accuracy (%): 85.11 -> 86.97Improved

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