Multi-Agent Reinforcement Learning on CN rac-dist
888Mean Episodic RewardDRE-MARL
Evaluation results
| Method | Links | |
|---|---|---|
| DRE-MARLq=72022.10 | 888 | |
| MADDPGq=72022.10 | 802 | |
| DRE-MARLq=32022.10 | 477 | |
| MADDPGq=32022.10 | 476 | |
| QMIXq=32022.10 | 367 | |
| p2p-MARLq=32022.10 | 271 | |
| MAPPOq=32022.10 | 156 | |
| DRE-MARLq=102022.10 | 133 | |
| MAACq=72022.10 | -85 | |
| MAACq=32022.10 | -98 | |
| MADDPGq=102022.10 | -122 | |
| p2p-MARLq=72022.10 | -480 | |
| IQLq=32022.10 | -2,645 | |
| p2p-MARLq=102022.10 | -2,900 | |
| MAPPOq=72022.10 | -2,960 | |
| MAACq=102022.10 | -3,036 | |
| QMIXq=72022.10 | -7,122 | |
| MAPPOq=102022.10 | -7,379 | |
| QMIXq=102022.10 | -16,977 | |
| IQLq=72022.10 | -24,492 | |
| IQLq=102022.10 | -59,231 |