AI Paper Atlas

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

Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning

Woojun Kim, Myungsik Cho, Youngchul Sung

AAAI 2019 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Learned inter-agent communication · 55 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
Apply message-dropout with a proper dropout rateDCC in pursuit · Pursuit (N=6, N=8)evader catchesImproved
Apply message-dropout with dropout rate 0.2 or 0.5DCC · Cooperative navigation (N=8, L=8; N=10, L=10)sum of agents' rewardsImproved
Apply message-dropout with dropout rate 0.2 or 0.5MADDPG · Waterworld (N=8, K=4; N=10, K=5)food target catchesImproved
Use message-dropout during trainingDCC · Pursuit with half of communication links brokenevader catchesImproved
Use message-dropout during trainingDCC · Pursuit with all communication links brokenevader catchesHurt
Increase dropout rate (ablation)DCC-MD · Pursuit traininglearning speedImproved
Use dropout rates 0.2 to 0.5 rather than other tested rates (ablation)DCC-MD · Pursuit executionevader catchesNo clear effect
Use block-wise message-dropout instead of element-wise standard dropout (ablation)DCC · PursuitperformanceImproved
Keep each agent's own observation undropped (ablation)DCC with message-dropout · Pursuittraining timeImproved
Apply dropout to each agent's own observation as well as other agents' messages (ablation)DCC · Pursuittraining timeHurt
Use the observation/message-separated Q-function architecture instead of concatenated inputs (ablation)DCC-MD · Pursuit (N=8) and Waterworldlearning successImproved
Compress messages with an autoencoder (ablation)DCC and DCC-MD · Pursuit (N=8)steady-state performanceHurt

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