AI Paper Atlas

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

Learning to Schedule Communication in Multi-agent Reinforcement Learning

Daewoo Kim, Sangwoo Moon, David Hostallero, Wan Ju Kang, Taeyoung Lee, Kyunghwan Son, Yung Yi

ICLR 2019 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Learned inter-agent communication · 56 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
use learned Top(1) scheduling instead of round-robin schedulingSchedNet · Predator and Prey (PP)task performance: 43%Improved
use learned scheduling instead of round-robin schedulingSchedNet · Cooperative Communication and Navigation (CCN)time to complete task: 32%Improved
use learned Top(1) scheduling rather than Softmax(1) schedulingSchedNet · Predator and Prey (PP)time to capture preyImproved
use learned Top(1) scheduling rather than Softmax(1) schedulingSchedNet · Cooperative Communication and Navigation (CCN)time to complete taskImproved
add communication with learned schedulingSchedNet · Predator and Prey (PP)time to capture preyImproved
add communication with learned schedulingSchedNet · Cooperative Communication and Navigation (CCN)time to complete taskImproved
train the encoder jointly with the scheduler and action network instead of fixing a pre-trained auto-encoder (ablation)SchedNet-Top(1) · Predator and Prey (PP)time to complete task, normalized to FC: 3.408 -> 2.030Improved
use communication with learned scheduling rather than no communication (ablation)SchedNet · Predator and Prey (PP)time to capture preyImproved
increase message bandwidth (ablation)SchedNet · Predator and Prey (PP)time to complete taskImproved
increase the number of agents allowed to broadcast (ablation)SchedNet · Predator and Prey (PP)time to complete taskImproved
add a GRU layer to the encoder, action selector, and weight generator (ablation)SchedNet · Predator and Prey (PP)average steps to complete taskNo clear effect
add a GRU layer to the network (ablation)IDQN · Predator and Prey (PP)average steps to complete taskImproved

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