Multi-Agent Reinforcement Learning on CN rdete
-154Mean Episodic RewardDRE-MARL
Evaluation results
| Method | Links | |
|---|---|---|
| DRE-MARLq=32022.10 | -154 | |
| p2p-MARLq=32022.10 | -167 | |
| MADDPGq=32022.10 | -169 | |
| MAACq=32022.10 | -227 | |
| MAPPOq=32022.10 | -425 | |
| IQLq=32022.10 | -738 | |
| QMIXq=32022.10 | -1,168 | |
| DRE-MARLq=72022.10 | -3,070 | |
| p2p-MARLq=72022.10 | -3,101 | |
| MAACq=72022.10 | -3,293 | |
| MADDPGq=72022.10 | -3,428 | |
| IQLq=72022.10 | -5,092 | |
| MAPPOq=72022.10 | -5,674 | |
| DRE-MARLq=102022.10 | -8,138 | |
| p2p-MARLq=102022.10 | -8,418 | |
| MAACq=102022.10 | -8,555 | |
| MADDPGq=102022.10 | -8,938 | |
| QMIXq=72022.10 | -9,320 | |
| IQLq=102022.10 | -12,658 | |
| MAPPOq=102022.10 | -13,375 | |
| QMIXq=102022.10 | -21,858 |