AI Paper Atlas

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

Learning Robust Multi-Agent Policies via Selective Adversarial Fault Induction

David Henry Mguni, Yaqi Sun, Haojun Chen, Wanrong Yang, Amir Darabi, Larry Olanrewaju Orimoloye, Yaodong Yang

ICML 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms

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
add MARTA switcher-adversary trainingQMIX · Traffic Junctionfinal test return: -54.2 -> -48.2Improved
add MARTA trainingQMIX · LBF-5x5-4p-1ffinal test return: 0.65 -> 0.94Improved
add MARTA trainingQMIX · SMACv2 3mfinal test return: 1.14 -> 2.45Improved
add MARTA trainingVDN · SMACv2 3mfinal test return: 2.57 -> 5.57Improved
add MARTA trainingVDN · LBF-5x5-4p-1ffinal test return: 0.94 -> 0.97No clear effect
add MARTA trainingVDN · Traffic Junctioncollision/failure rate (%): 17.5 -> 5.0Improved
replace learned Switcher with Bernoulli random trigger (ablation)MARTA · MPE SimpleTagtest returnHurt
add MARTA to MADDPG backbone vs M3DDPGMADDPG · MPE SimpleTagtest returnImproved
compare MARTA to EIR under aligned fixed fault (Case 1)EIR · TJ, LBF, MPE, SMAC-3mrobustness metricsNo clear effect
compare MARTA to EIR under dynamic faults (Case 2)EIR · TJ, LBF, MPE, SMAC-3mrobustness metricsImproved
increase switch cost c (ablation)MARTA · Traffic Junctionfault activationsMixed
add MARTA under higher malfunction probability p (ablation)QMIX · Traffic Junctionfinal returnImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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