Multi-Agent Reinforcement Learning on REF rdete
-44Mean Episodic RewardMADDPG
Evaluation results
| Method | Links | |
|---|---|---|
| MADDPGq=22022.10 | -44 | |
| DRE-MARLq=22022.10 | -54 | |
| p2p-MARLq=22022.10 | -58 | |
| MAACq=22022.10 | -69 | |
| MAPPOq=22022.10 | -85 | |
| IQLq=22022.10 | -95 | |
| QMIXq=22022.10 | -438 | |
| DRE-MARLq=72022.10 | -732 | |
| p2p-MARLq=72022.10 | -808 | |
| MAACq=72022.10 | -1,120 | |
| MADDPGq=72022.10 | -1,133 | |
| MAPPOq=72022.10 | -1,187 | |
| QMIXq=72022.10 | -1,359 | |
| DRE-MARLq=102022.10 | -1,524 | |
| p2p-MARLq=102022.10 | -1,542 | |
| MAACq=102022.10 | -2,380 | |
| IQLq=72022.10 | -2,400 | |
| MADDPGq=102022.10 | -3,102 | |
| MAPPOq=102022.10 | -3,317 | |
| QMIXq=102022.10 | -4,037 | |
| IQLq=102022.10 | -4,921 |