# Dexterous Grasping with Real-World Robotic Reinforcement Learning

arXiv: https://arxiv.org/abs/2503.04014 · HTML: https://mlsanity.com/paper/2503.04014/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## 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, 23 of 23)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [Deep Dynamics Models for Learning Dexterous Manipulation](https://mlsanity.com/paper/1909.11652/) (2019)
- [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024)
- [DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation](https://mlsanity.com/paper/2403.07788/) (2024)
- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://mlsanity.com/paper/2401.16013/) (2024)
- [Jump-Start Reinforcement Learning](https://mlsanity.com/paper/2204.02372/) (2022)
- [UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning](https://mlsanity.com/paper/2304.00464/) (2023)
- [Offline Reinforcement Learning from Images with Latent Space Models](https://mlsanity.com/paper/2012.11547/) (2020)
- [Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost](https://mlsanity.com/paper/1810.06045/) (2018)
- [A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning](https://mlsanity.com/paper/2208.07860/) (2022)
- [Watch and Match: Supercharging Imitation with Regularized Optimal Transport](https://mlsanity.com/paper/2206.15469/) (2022)
- [Learning Generalizable Dexterous Manipulation from Human Grasp Affordance](https://mlsanity.com/paper/2204.02320/) (2022)
- [DexGraspNet 2.0: Learning Generative Dexterous Grasping in Large-scale Synthetic Cluttered Scenes](https://mlsanity.com/paper/2410.23004/) (2024)
- [RealDex: Towards Human-like Grasping for Robotic Dexterous Hand](https://mlsanity.com/paper/2402.13853/) (2024)
- [MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning](https://mlsanity.com/paper/2410.14972/) (2024)
- [DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal Human Demonstrations](https://mlsanity.com/paper/2209.14284/) (2022)
- [Leveraging Fully Observable Policies for Learning under Partial Observability](https://mlsanity.com/paper/2211.01991/) (2022)
- [UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping](https://mlsanity.com/paper/2412.02699/) (2024)

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

- [EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling](https://mlsanity.com/paper/2507.05198/) (2025)
- [AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection](https://mlsanity.com/paper/2606.23689/) (2026)

## Abstract (arXiv)

Dexterous grasping in the real world presents a fundamental and significant challenge for robot learning. The ability to employ affordance-aware poses to grasp objects with diverse geometries and properties in arbitrary scenarios is essential for general-purpose robots. However, existing research predominantly addresses dexterous grasping problems within simulators, which encounter difficulties when applied in real-world environments due to the domain gap between reality and simulation. This limitation hinders their generalizability and practicality in real-world applications. In this paper, we present DexGraspRL, a reinforcement learning (RL) framework that directly trains robots in real-world environments to acquire dexterous grasping skills. Specifically, DexGraspRL consists of two stages: (i) a pretraining stage that pretrains the policy using imitation learning (IL) with a limited set of expert demonstrations; (ii) a fine-tuning stage that refines the policy through direct RL in real-world scenarios. To mitigate the catastrophic forgetting phenomenon arising from the distribution shift between demonstrations and real-world environments, we design a regularization term that balances the exploitation of RL with the preservation of the pretrained policy. Our experiments with real-world tasks demonstrate that DexGraspRL successfully accomplishes diverse dexterous grasping tasks, achieving an average success rate of nearly 92%. Furthermore, by fine-tuning with RL, our method uncovers novel policies, surpassing the IL policy with a 23% reduction in average cycle time.