AI Paper Atlas

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

Robust Multi-Agent Reinforcement Learning with Model Uncertainty

Kaiqing Zhang, TAO SUN, Yunzhe Tao, Sahika Genc, Sunil Mallya, Tamer Basar

NeurIPS 2020 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 28 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
train with R-MADDPG instead of MADDPG/M3DDPG under high reward uncertaintyMADDPG · Cooperative navigationlandmark occupation success rateImproved
R-MADDPG agent and adversary instead of MADDPG pairMADDPG · Keep-away, λ = 3.0agent steps occupying target: 1.37 -> 5.26Improved
use R-MADDPG vs MADDPG when no uncertaintyMADDPG · Keep-away, λ = 0agent steps occupying target: 16.76 -> 5.22Hurt
R-MADDPG agents vs MADDPG agents against R-MADDPG adversaryMADDPG · Physical deception, λ > 0agent success rate and distance: 0.68 -> 0.86 (AG succ, λ=2.0)Improved
R-MADDPG prey instead of MADDPG prey against MADDPG predatorsMADDPG · Predator-prey, λ = 1.0prey touches per episode: 2.38 -> 1.61Improved
R-MADDPG predators instead of MADDPG against MADDPG preyMADDPG · Predator-prey, λ = 3.0prey touches per episode: 3.20 -> 4.64Improved

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