# Learning Hybrid-Control Policies for High-Precision In-Contact Manipulation Under Uncertainty

arXiv: https://arxiv.org/abs/2604.19677 · HTML: https://mlsanity.com/paper/2604.19677/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks](https://mlsanity.com/paper/1810.10191/) (2018)
- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://mlsanity.com/paper/2401.16013/) (2024)
- [Policy Representation via Diffusion Probability Model for Reinforcement Learning](https://mlsanity.com/paper/2305.13122/) (2023)
- [SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.09754/) (2024)
- [Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks](https://mlsanity.com/paper/1906.08880/) (2019)
- [Factory: Fast Contact for Robotic Assembly](https://mlsanity.com/paper/2205.03532/) (2022)
- [IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Reality](https://mlsanity.com/paper/2305.17110/) (2023)
- [Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics](https://mlsanity.com/paper/2001.00449/) (2020)
- [Robust Multi-Modal Policies for Industrial Assembly via Reinforcement Learning and Demonstrations: A Large-Scale Study](https://mlsanity.com/paper/2103.11512/) (2021)
- [A Survey of Robot Manipulation in Contact](https://mlsanity.com/paper/2112.01942/) (2021)
- [Learning Gentle Object Manipulation with Curiosity-Driven Deep Reinforcement Learning](https://mlsanity.com/paper/1903.08542/) (2019)
- [Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces](https://mlsanity.com/paper/1905.04388/) (2019)
- [FORGE: Force-Guided Exploration for Robust Contact-Rich Manipulation under Uncertainty](https://mlsanity.com/paper/2408.04587/) (2024)
- [Efficient Sim-to-real Transfer of Contact-Rich Manipulation Skills with Online Admittance Residual Learning](https://mlsanity.com/paper/2310.10509/) (2023)
- [Compare Contact Model-based Control and Contact Model-free Learning: A Survey of Robotic Peg-in-hole Assembly Strategies](https://mlsanity.com/paper/1904.05240/) (2019)
- [AugInsert: Learning Robust Visual-Force Policies via Data Augmentation for Object Assembly Tasks](https://mlsanity.com/paper/2410.14968/) (2024)

## Abstract (arXiv)

Reinforcement learning-based control policies have been frequently demonstrated to be more effective than analytical techniques for many manipulation tasks. Commonly, these methods learn neural control policies that predict end-effector pose changes directly from observed state information. For tasks like inserting delicate connectors which induce force constraints, pose-based policies have limited explicit control over force and rely on carefully tuned low-level controllers to avoid executing damaging actions. In this work, we present hybrid position-force control policies that learn to dynamically select when to use force or position control in each control dimension. To improve learning efficiency of these policies, we introduce Mode-Aware Training for Contact Handling (MATCH) which adjusts policy action probabilities to explicitly mirror the mode selection behavior in hybrid control. We validate MATCH's learned policy effectiveness using fragile peg-in-hole tasks under extreme localization uncertainty. We find MATCH substantially outperforms pose-control policies -- solving these tasks with up to 10% higher success rates and 5x fewer peg breaks than pose-only policies under common types of state estimation error. MATCH also demonstrates data efficiency equal to pose-control policies, despite learning in a larger and more complex action space. In over 1600 sim-to-real experiments, we find MATCH succeeds twice as often as pose policies in high noise settings (33% vs.~68%) and applies ~30% less force on average compared to variable impedance policies on a Franka FR3 in laboratory conditions.