Cooperative Multi-Agent Reinforcement Learning on Rover-Tower 4 rovers and 4 towers scenario
40FCommTransfQmix
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| TransfQmix2025.02 | 40 | 98 | 0 | |
| AsyncMAPPO2025.02 | 24 | 98 | 0 | |
| Actor-Attention-Critic2025.02 | 21 | 84 | 56 | |
| AsynCoMARL2025.02 | 14 | 55 | 50 |