HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Smac On Smac Off Near Parallel

評価指標

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

モデル名
Median Win Rate
Paper TitleRepository
QMIX95.0QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
DIQL0.0DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
COMA20.0Counterfactual Multi-Agent Policy Gradients
DDN0.0DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
QTRAN0.0QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
IQL5.0--
DMIX0.0DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
MASAC0.0Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning
VDN90.0Value-Decomposition Networks For Cooperative Multi-Agent Learning
DRIMA95.0Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning-
0 of 10 row(s) selected.