Smac On Smac Off Superhard Sequential

Median Win Rate

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

		Paper Title
DRIMA	15.6	Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
QMIX	0.0	QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
MADDPG	0.0	Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
COMA	0.0	Counterfactual Multi-Agent Policy Gradients

0 of 4 row(s) selected.