Multi-Agent Reinforcement Learning on TREA rdete
-390Mean Episodic RewardQMIX
Evaluation results
| Method | Links | |
|---|---|---|
| QMIXq=32022.10 | -390 | |
| MADDPGq=32022.10 | -428 | |
| p2p-MARLq=32022.10 | -457 | |
| DRE-MARLq=32022.10 | -458 | |
| MAACq=32022.10 | -480 | |
| MAPPOq=32022.10 | -671 | |
| IQLq=32022.10 | -924 | |
| p2p-MARLq=72022.10 | -2,638 | |
| DRE-MARLq=72022.10 | -2,641 | |
| MADDPGq=72022.10 | -2,678 | |
| MAACq=72022.10 | -2,809 | |
| QMIXq=72022.10 | -3,324 | |
| MAPPOq=72022.10 | -3,648 | |
| IQLq=72022.10 | -4,733 | |
| MAACq=102022.10 | -4,931 | |
| DRE-MARLq=102022.10 | -5,076 | |
| p2p-MARLq=102022.10 | -5,260 | |
| MADDPGq=102022.10 | -5,699 | |
| MAPPOq=102022.10 | -6,864 | |
| IQLq=102022.10 | -8,465 | |
| QMIXq=102022.10 | -8,715 |