ResearchBenchmarksCooperative Multi-Agent Reinforcement Learning on Crypto (last 2% of train)Follow50Mean Episodic RewardDCG-16.91360.458217.8335.2018May 8, 2026Evaluation ResultsMethodMethodLinksMean Episodic RewardDCG2026.0550SACHIL=2, d=64, K=1L=2, d=64, K=12026.0548DGN2026.0548VDN2026.0547.7QTRAN2026.0546.07CASEC2026.0543.9IQL2026.0542.38FOP2026.0523.69DICG2026.0513.35QPLEX2026.058.98IPPO2026.057.99MAPPO2026.057.31QMIX2026.05-14.34