# Lessons from Learning to Spin "Pens"

arXiv: https://arxiv.org/abs/2407.18902 · HTML: https://mlsanity.com/paper/2407.18902/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 64 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 30 of 50)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation](https://mlsanity.com/paper/2403.07788/) (2024)
- [AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System](https://mlsanity.com/paper/2307.04577/) (2023)
- [DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality](https://mlsanity.com/paper/2210.13702/) (2022)
- [Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation](https://mlsanity.com/paper/2403.03949/) (2024)
- [Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning](https://mlsanity.com/paper/2206.08686/) (2022)
- [In-Hand Object Rotation via Rapid Motor Adaptation](https://mlsanity.com/paper/2210.04887/) (2022)
- [3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations](https://mlsanity.com/paper/2403.03954/) (2024)
- [UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning](https://mlsanity.com/paper/2304.00464/) (2023)
- [Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes](https://mlsanity.com/paper/2211.11744/) (2022)
- [General In-Hand Object Rotation with Vision and Touch](https://mlsanity.com/paper/2309.09979/) (2023)
- [se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains](https://mlsanity.com/paper/2007.13866/) (2020)
- [DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation](https://mlsanity.com/paper/2211.09423/) (2022)
- [Rotating without Seeing: Towards In-hand Dexterity through Touch](https://mlsanity.com/paper/2303.10880/) (2023)
- [From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation](https://mlsanity.com/paper/2204.12490/) (2022)
- [LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning](https://mlsanity.com/paper/2309.06440/) (2023)
- [Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation](https://mlsanity.com/paper/2203.13251/) (2022)
- [Learning Visuotactile Skills with Two Multifingered Hands](https://mlsanity.com/paper/2404.16823/) (2024)
- [Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations](https://mlsanity.com/paper/2303.01497/) (2023)
- [OPEN TEACH: A Versatile Teleoperation System for Robotic Manipulation](https://mlsanity.com/paper/2403.07870/) (2024)
- [DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects](https://mlsanity.com/paper/2305.05706/) (2023)
- [TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction](https://mlsanity.com/paper/2405.10315/) (2024)
- [Holo-Dex: Teaching Dexterity with Immersive Mixed Reality](https://mlsanity.com/paper/2210.06463/) (2022)
- [Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing](https://mlsanity.com/paper/2312.01853/) (2023)

## Built on by (most cited first, 26 of 26)

- [Residual Off-Policy RL for Finetuning Behavior Cloning Policies](https://mlsanity.com/paper/2509.19301/) (2025)
- [Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids](https://mlsanity.com/paper/2502.20396/) (2025)
- [FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model](https://mlsanity.com/paper/2412.08261/) (2024)
- [SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation](https://mlsanity.com/paper/2602.16863/) (2026)
- [Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation](https://mlsanity.com/paper/2602.15828/) (2026)
- [VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning](https://mlsanity.com/paper/2510.14930/) (2025)
- [Scaffolding Dexterous Manipulation with Vision-Language Models](https://mlsanity.com/paper/2506.19212/) (2025)
- [DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model](https://mlsanity.com/paper/2510.08556/) (2025)
- [Learning Dexterous Manipulation Skills from Imperfect Simulations](https://mlsanity.com/paper/2512.02011/) (2025)
- [From Simple to Complex Skills: The Case of In-Hand Object Reorientation](https://mlsanity.com/paper/2501.05439/) (2025)
- [RUKA: Rethinking the Design of Humanoid Hands with Learning](https://mlsanity.com/paper/2504.13165/) (2025)
- [TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation](https://mlsanity.com/paper/2606.16272/) (2026)
- [SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training](https://mlsanity.com/paper/2507.04452/) (2025)
- [House of Dextra: Cross-embodied Co-design for Dexterous Hands](https://mlsanity.com/paper/2512.03743/) (2025)
- [FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control](https://mlsanity.com/paper/2604.04539/) (2026)
- [LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations](https://mlsanity.com/paper/2508.17547/) (2025)
- [A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation](https://mlsanity.com/paper/2607.11874/) (2026)
- [Composing Dextrous Grasping and In-hand Manipulation via Scoring with a Reinforcement Learning Critic](https://mlsanity.com/paper/2505.13253/) (2025)
- [Learning to Play Piano in the Real World](https://mlsanity.com/paper/2503.15481/) (2025)
- [Learning Adaptive Dexterous Grasping from Single Demonstrations](https://mlsanity.com/paper/2503.20208/) (2025)
- [MILE: A Mechanically Isomorphic Hand Exoskeleton and Visuotactile Robotic Hand for Data Collection in Dexterous Manipulation](https://mlsanity.com/paper/2512.00324/) (2025)
- [Diffusing Trajectory Optimization Problems for Recovery During Multi-Finger Manipulation](https://mlsanity.com/paper/2510.07030/) (2025)
- [DexMani: Human-Derived Manipulability Guidance for Dexterous Rotation](https://mlsanity.com/paper/2608.00554/) (2026)
- [Object Pose Estimation through Dexterous Touch](https://mlsanity.com/paper/2509.13591/) (2025)
- [HandelBot: Real-World Piano Playing via Fast Adaptation of Dexterous Robot Policies](https://mlsanity.com/paper/2603.12243/) (2026)
- [Mana: Dexterous Manipulation of Articulated Tools](https://mlsanity.com/paper/2606.13677/) (2026)

## Abstract (arXiv)

In-hand manipulation of pen-like objects is an important skill in our daily lives, as many tools such as hammers and screwdrivers are similarly shaped. However, current learning-based methods struggle with this task due to a lack of high-quality demonstrations and the significant gap between simulation and the real world. In this work, we push the boundaries of learning-based in-hand manipulation systems by demonstrating the capability to spin pen-like objects. We first use reinforcement learning to train an oracle policy with privileged information and generate a high-fidelity trajectory dataset in simulation. This serves two purposes: 1) pre-training a sensorimotor policy in simulation; 2) conducting open-loop trajectory replay in the real world. We then fine-tune the sensorimotor policy using these real-world trajectories to adapt it to the real world dynamics. With less than 50 trajectories, our policy learns to rotate more than ten pen-like objects with different physical properties for multiple revolutions. We present a comprehensive analysis of our design choices and share the lessons learned during development.