Goal-navigation on Two Rooms custom (Room 2)
-17ReturnCIC
Evaluation Results
| Method | Links | |
|---|---|---|
| CICAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -17 | |
| ROVERAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -17 | |
| ROVERAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -17 | |
| DDPG (online)Training protocol=50k interactions2026.06 | -17 | |
| RandomAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -32 | |
| RandomAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -35 | |
| CICAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -71.2 | |
| APTAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -80 | |
| SMMAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -80 | |
| RNDAlgorithm=CQL, Training protocol=15k gradient updates2026.06 | -80 | |
| APTAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -80 | |
| SMMAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -80 | |
| RNDAlgorithm=DDPG, Training protocol=15k gradient updates2026.06 | -80 |