Multi-Agent Reinforcement Learning on hallway
55.4AUCMUTE
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MUTE2026.07 | 55.4 | — | — | |
| MAIC2026.07 | 17.8 | — | — | |
| MASIA2026.07 | 13.1 | — | — | |
| IC3Net2026.07 | 4.8 | — | — | |
| SMS2026.07 | 0.1 | — | — | |
| TarMAC2026.07 | 0 | — | — | |
| MUTETraining Step Budget Allocation=4M total (2M pre-training, 0.5M MVE, 1.5M unlearning)2026.07 | — | 97 | 2 | |
| TDCommunication Penalty (+pnlt)=true, Gating Mechanism=false, Training Step Budget Allocation=4M steps standard RL2026.07 | — | 100 | 56 | |
| TDCommunication Penalty (+pnlt)=true, Gating Mechanism=true, Training Step Budget Allocation=4M steps standard RL2026.07 | — | 100 | 43 | |
| TDCommunication Penalty (+pnlt)=false, Gating Mechanism=false, Training Step Budget Allocation=4M steps standard RL2026.07 | — | 100 | 100 | |
| TDCommunication Penalty (+pnlt)=false, Gating Mechanism=true, Training Step Budget Allocation=4M steps standard RL2026.07 | — | 100 | 98 |