Multi-agent reinforcement learning on Simple Adversary Unrestricted
-5.8Avg Episode Cumulative RewardCC-MADDPG
Evaluation results
| Method | Links | |
|---|---|---|
| CC-MADDPG2025.12 | -5.8 | |
| Dropout-MADDPGDropout Rate=0.52025.12 | -6.6 | |
| FC-MADDPG2025.12 | -6.7 | |
| Dropout-MADDPGDropout Rate=0.82025.12 | -6.7 | |
| Dropout-MADDPGDropout Rate=0.22025.12 | -6.8 | |
| MAIC2025.12 | -29.5 | |
| MADDPG2025.12 | -75.5 |