Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning
- Published
- Source
- arXiv
- Paper number
- 1167
- Field
- Robotics
- arXiv ID
- 2610.05882
Key points
- They observed that 95% of failures concentrate in 25% of the initial states, so uniform collection wastes operator time.
- By retrying failed states and filling in unexplored ones, the robot learned faster under the same collection budget.
- Combining a value function that also learns from failures (HiL-IDQL+Mulligan) improved final real-task success by 10-34 percentage points.
- They validated the results on 2,550 blinded held-out episodes for higher reliability.
Paper links
External research summaries. These are not HDATF publications or measured product results.