Exploiting Policy Idling for Dexterous Manipulation

August 21, 2025 Β· Declared Dead Β· πŸ› IEEE/RJS International Conference on Intelligent RObots and Systems

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Annie S. Chen, Philemon Brakel, Antonia Bronars, Annie Xie, Sandy Huang, Oliver Groth, Maria Bauza, Markus Wulfmeier, Nicolas Heess, Dushyant Rao arXiv ID 2508.15669 Category cs.RO: Robotics Cross-listed cs.LG Citations 0 Venue IEEE/RJS International Conference on Intelligent RObots and Systems Last Checked 6 months ago
Abstract
Learning-based methods for dexterous manipulation have made notable progress in recent years. However, learned policies often still lack reliability and exhibit limited robustness to important factors of variation. One failure pattern that can be observed across many settings is that policies idle, i.e. they cease to move beyond a small region of states when they reach certain states. This policy idling is often a reflection of the training data. For instance, it can occur when the data contains small actions in areas where the robot needs to perform high-precision motions, e.g., when preparing to grasp an object or object insertion. Prior works have tried to mitigate this phenomenon e.g. by filtering the training data or modifying the control frequency. However, these approaches can negatively impact policy performance in other ways. As an alternative, we investigate how to leverage the detectability of idling behavior to inform exploration and policy improvement. Our approach, Pause-Induced Perturbations (PIP), applies perturbations at detected idling states, thus helping it to escape problematic basins of attraction. On a range of challenging simulated dual-arm tasks, we find that this simple approach can already noticeably improve test-time performance, with no additional supervision or training. Furthermore, since the robot tends to idle at critical points in a movement, we also find that learning from the resulting episodes leads to better iterative policy improvement compared to prior approaches. Our perturbation strategy also leads to a 15-35% improvement in absolute success rate on a real-world insertion task that requires complex multi-finger manipulation.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Robotics

Died the same way β€” πŸ‘» Ghosted