Multi-Agent Reinforcement Learning on TREA rdist
32,421Mean Episodic RewardMADDPG
Evaluation Results
| Method | Links | |
|---|---|---|
| MADDPGq=102022.10 | 32,421 | |
| MAPPOq=102022.10 | 31,878 | |
| DRE-MARLq=102022.10 | 29,193 | |
| QMIXq=102022.10 | 27,100 | |
| p2p-MARLq=102022.10 | 20,437 | |
| MAACq=102022.10 | 17,306 | |
| MADDPGq=72022.10 | 15,436 | |
| MAPPOq=72022.10 | 14,473 | |
| QMIXq=72022.10 | 14,364 | |
| DRE-MARLq=72022.10 | 14,249 | |
| p2p-MARLq=72022.10 | 9,627 | |
| MAACq=72022.10 | 8,342 | |
| MAPPOq=32022.10 | 2,742 | |
| MADDPGq=32022.10 | 2,712 | |
| DRE-MARLq=32022.10 | 2,567 | |
| QMIXq=32022.10 | 2,384 | |
| MAACq=32022.10 | 1,776 | |
| p2p-MARLq=32022.10 | 1,708 | |
| QMIXq=32022.10 | -427 | |
| p2p-MARLq=32022.10 | -447 | |
| MADDPGq=32022.10 | -449 | |
| DRE-MARLq=32022.10 | -484 | |
| MAACq=32022.10 | -513 | |
| MAPPOq=32022.10 | -691 | |
| IQLq=32022.10 | -889 | |
| DRE-MARLq=72022.10 | -2,733 | |
| p2p-MARLq=72022.10 | -2,745 | |
| MADDPGq=72022.10 | -2,824 | |
| MAACq=72022.10 | -2,956 | |
| IQLq=32022.10 | -3,505 | |
| QMIXq=72022.10 | -3,553 | |
| MAPPOq=72022.10 | -3,741 | |
| IQLq=72022.10 | -5,092 | |
| MAACq=102022.10 | -5,306 | |
| DRE-MARLq=102022.10 | -5,340 | |
| p2p-MARLq=102022.10 | -5,515 | |
| MADDPGq=102022.10 | -5,847 | |
| MAPPOq=102022.10 | -6,912 | |
| IQLq=102022.10 | -8,727 | |
| QMIXq=102022.10 | -8,897 | |
| IQLq=72022.10 | -17,986 | |
| IQLq=102022.10 | -32,136 |