| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-agent Reinforcement Learning | Boxpushing | Reward145.35 | 15 | |
| Multi-agent coordination | Boxpushing (BP) | Base Score290.42 | 4 | |
| RNN-based cooperative multi-agent verification | BoxPushing (BP) 20x20 environment | Avg Violation Rate1.51 | 2 | |
| RNN-based cooperative multi-agent verification | BoxPushing (BP) 10x10 environment | Average Violation Rate1.15 | 2 |