ResearchBenchmarksMulti-Agent Reinforcement Learning on MPE Adversary (test)Multi-Agent Reinforcement Learning on MPE Adversary (test)Follow62.9Final Test ReturnLLM-Priors4.1419.39534.6549.905Apr 19, 2026Evaluation resultsMethodMethodLinksFinal Test ReturnLLM-Priors2026.0462.9DCG2026.0438.8DICG2026.0434.3IQL2026.0432.1VDN2026.0415.2QMIX2026.046.4