RoomVisit on CHORES (test)
68.3Success RateVLLR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VLLRLearning Regime=IL+RL, Reward Signal Type=Dense Reward2026.03 | 68.3 | 64.8 | |
| FLaReLearning Regime=IL+RL, Reward Signal Type=Sparse Reward2026.03 | 60.87 | 65.7 | |
| SPOCLearning Regime=IL Only2026.03 | 40.5 | 35.7 | |
| JSRLLearning Regime=IL+RL, Reward Signal Type=Sparse Reward2026.03 | 19 | 18.6 | |
| PIRLNavLearning Regime=IL+RL, Reward Signal Type=Sparse Reward2026.03 | 12.5 | 11 |