Goal-navigation on Multi Rooms Room 2 custom
-11ReturnAPT
Evaluation Results
| Method | Links | |
|---|---|---|
| APTAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -11 | |
| CICAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -11 | |
| RNDAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -11 | |
| ROVERAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -11 | |
| DDPG (online)Training protocol=50k interactions2026.06 | -11 | |
| ROVERAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -54.4 | |
| CICAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -91.6 | |
| APTAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -135.1 | |
| RNDAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -217.4 | |
| RandomAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -218.2 | |
| RandomAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -300 | |
| SMMAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -300 | |
| SMMAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -300 |