ResearchBenchmarksMixed-Motive Multi-Agent Reinforcement Learning on MPE simple_tagMixed-Motive Multi-Agent Reinforcement Learning on MPE simple_tagFollow227.69RewardMAPPO-2.004457.6278117.26176.8922Jun 9, 2026Evaluation resultsMethodMethodLinksRewardCumulative RegretRegret GapMAPPO2026.06227.691,084.682,192.3Φ-AC2026.0612.55481.5653.79MADDPG2026.066.831,409.982,321.88