Continual Instruction Following on VirtualHome
61.12SRExRAP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ExRAPNon-stationarity=Low2025.09 | 61.12 | 11.75 | |
| ExRAPNon-stationarity=Medium2025.09 | 55.14 | 11.33 | |
| ExRAPNon-stationarity=High2025.09 | 50.12 | 8.61 | |
| LLM-PlannerNon-stationarity=Low2025.09 | 40.97 | 17.61 | |
| LLM-PlannerNon-stationarity=Medium2025.09 | 39.89 | 15.93 | |
| SayCanNon-stationarity=Low2025.09 | 35.12 | 21.67 | |
| LLM-PlannerNon-stationarity=High2025.09 | 34.6 | 14.94 | |
| SayCanNon-stationarity=Medium2025.09 | 33.69 | 21.81 | |
| ProgPromptNon-stationarity=Low2025.09 | 32.1 | 18.84 | |
| ProgPromptNon-stationarity=Medium2025.09 | 30.51 | 23.43 | |
| SayCanNon-stationarity=High2025.09 | 27.33 | 16.18 | |
| ProgPromptNon-stationarity=High2025.09 | 27.19 | 18.6 | |
| ZSPNon-stationarity=Low2025.09 | 20.59 | 31.03 | |
| ZSPNon-stationarity=Medium2025.09 | 20.06 | 32.06 | |
| ZSPNon-stationarity=High2025.09 | 17.28 | 24.08 |