# Dexterous Pre-grasp Manipulation for Human-like Functional Categorical Grasping: Deep Reinforcement Learning and Grasp Representations

arXiv: https://arxiv.org/abs/2307.16752 · HTML: https://mlsanity.com/paper/2307.16752/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2023.

## Built on by (most cited first, 4 of 4)

- [Web2Grasp: Learning Functional Grasps from Web Images of Hand-Object Interactions](https://mlsanity.com/paper/2505.05517/) (2025)
- [Grasp Anything: Combining Teacher-Augmented Policy Gradient Learning with Instance Segmentation to Grasp Arbitrary Objects](https://mlsanity.com/paper/2403.10187/) (2024)
- [Placeit! A Framework for Learning Robot Object Placement Skills](https://mlsanity.com/paper/2510.09267/) (2025)
- [Scalable Dexterous Robot Learning with AR-based Remote Human-Robot Interactions](https://mlsanity.com/paper/2602.07341/) (2026)

## Abstract (arXiv)

Many objects, such as tools and household items, can be used only if grasped in a very specific way - grasped functionally. Often, a direct functional grasp is not possible, though. We propose a method for learning a dexterous pre-grasp manipulation policy to achieve human-like functional grasps using deep reinforcement learning. We introduce a dense multi-component reward function that enables learning a single policy, capable of dexterous pre-grasp manipulation of novel instances of several known object categories with an anthropomorphic hand. The policy is learned purely by means of reinforcement learning from scratch, without any expert demonstrations. It implicitly learns to reposition and reorient objects of complex shapes to achieve given functional grasps. In addition, we explore two different ways to represent a desired grasp: explicit and more abstract, constraint-based. We show that our method consistently learns to successfully manipulate and achieve desired grasps on previously unseen object instances of known categories using both grasp representations. Training is completed on a single GPU in under three hours.