HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Smac On Smac Off Near Sequential

Metriken

Median Win Rate

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
DRIMA93.8Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
QMIX90.6QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
MADDPG75.0Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
COMA0.0Counterfactual Multi-Agent Policy Gradients
0 of 4 row(s) selected.