Mn Evaluation Results
task_config = demo_clean, instruction_type = unseen, 100 episodes per task.
Each task is evaluated with its own separately trained execution-module checkpoint
and its own normalization stats.
| Task | action_horizon | Success Rate | Reward |
|---|---|---|---|
| battery_try | 15 | 0.21 | 0.00 |
| blocks_ranking_try | 15 | 0.15 | 0.00 |
| cover_blocks | 8 | 0.76 | 0.82 |
| press_button | 30 | 0.02 | 0.00 |
| Average | — | 0.285 | — |
Action horizon
Per-task inference-time action_horizon settings:
battery_try— 15blocks_ranking_try— 15cover_blocks— 8press_button— 30
All results above were produced with these values.
Files
<task>/episode0.mp4 … episode99.mp4— full rollout videos (100 per task)<task>/_result.txt— raw score file for that run