Multi-agent Path Planning on Simulated 32x32 Grids 5 targets
99Success RateMAPPO-based reinforcement learning framework
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MAPPO-based reinforcement learning frameworkPolicy=Π5T, Number of targets=52026.04 | 99 | 0.86 | 0.92 |
Loading the SOTA2 catalog…