# DexCtrl: Towards Sim-to-Real Dexterity with Adaptive Controller Learning

arXiv: https://arxiv.org/abs/2505.00991 · HTML: https://mlsanity.com/paper/2505.00991/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2025.

## Built on by (most cited first, 2 of 2)

- [DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model](https://mlsanity.com/paper/2510.08556/) (2025)
- [CARF: Contrastive Attraction-Repulsion of Failure-Guided Flow Matching](https://mlsanity.com/paper/2609.21982/) (2026)

## Abstract (arXiv)

Dexterous manipulation has seen remarkable progress in recent years, with policies capable of executing many complex and contact-rich tasks in simulation. However, transferring these policies from simulation to real world remains a significant challenge. One important issue is the mismatch in low-level controller dynamics, where identical trajectories can lead to vastly different contact forces and behaviors when control parameters vary. Existing approaches often rely on manual tuning or controller randomization, which can be labor-intensive, task-specific, and introduce significant training difficulty. In this work, we propose a framework that jointly learns actions and controller parameters based on the historical information of both trajectory and controller. This adaptive controller adjustment mechanism allows the policy to automatically tune control parameters during execution, thereby mitigating the sim-to-real gap without extensive manual tuning or excessive randomization. Moreover, by explicitly providing controller parameters as part of the observation, our approach facilitates better reasoning over force interactions and improves robustness in real-world scenarios. Experimental results demonstrate that our method achieves improved transfer performance across a variety of dexterous tasks involving variable force conditions.