Multi-Agent Reinforcement Learning on CN-q rac-dist (test)
144Mean Episodic Reward (q=3)DRE-MARL
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| DRE-MARLAggregation Scheme=l_MO + g_MO, Training Reward=Individual, Evaluation Setting=rac-dist2022.10 | 144 | 43 | -163 | 9.36 | |
| MADDPGTraining Reward=Individual, Evaluation Setting=rac-dist2022.10 | 138 | 47 | -217 | 4.608 | |
| DRE-MARLAggregation Scheme=l_SMO + g_ss, Training Reward=Individual, Evaluation Setting=rac-dist2022.10 | 133 | 39 | -86 | 7.904 | |
| MAACTraining Reward=Individual, Evaluation Setting=rac-dist2022.10 | 132 | 34 | -146 | 7.324 | |
| DRE-MARLAggregation Scheme=l_ss + g_ss, Training Reward=Individual, Evaluation Setting=rac-dist2022.10 | 129 | 36 | -122 | 7.893 | |
| DRE-MARLAggregation Scheme=l_SMO + g_MO, Training Reward=Individual, Evaluation Setting=rac-dist2022.10 | 126 | 11 | -172 | 8.467 | |
| GRE-MARLTraining Reward=Individual, Evaluation Setting=rac-dist2022.10 | 113 | -18 | -249 | 8.171 | |
| DRE-MARLAggregation Scheme=l_SMO, Training Reward=Individual, Evaluation Setting=rac-dist2022.10 | 99 | 1 | -186 | 7.737 | |
| p2p-MARLTraining Reward=Individual, Evaluation Setting=rac-dist2022.10 | 92 | -15 | -171 | 7.517 | |
| MAPPOTraining Reward=Individual, Evaluation Setting=rac-dist2022.10 | 10 | -313 | -686 | 2.457 | |
| QMIXTraining Reward=Individual, Evaluation Setting=rac-dist2022.10 | -4 | -209 | -315 | 5.97 | |
| IQLTraining Reward=Individual, Evaluation Setting=rac-dist2022.10 | -66 | -309 | -705 | 1.204 |