Share your thoughts, 1 month free Claude Pro on usSee more

Cooperative Multi-Agent Reinforcement Learning on Crypto (last 2% of train)

50Mean Episodic Reward

DCG

Updated 2mo ago

Evaluation Results

Method	Links
DCG 2026.05		50
SACHI 2026.05		48
DGN 2026.05		48
VDN 2026.05		47.7
QTRAN 2026.05		46.07
CASEC 2026.05		43.9
IQL 2026.05		42.38
FOP 2026.05		23.69
DICG 2026.05		13.35
QPLEX 2026.05		8.98
IPPO 2026.05		7.99
MAPPO 2026.05		7.31
QMIX 2026.05		-14.34