Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?

arXiv:2606.26428 · cs.RO, cs.AI · Submitted 2026-06-24 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-06-24

Updated: 2026-09-08

Comments: 25 pages, 19 figures, 4 tables. Project page: https://play2perfect.github.io

Project page: https://play2perfect.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Ablation — 13× in this paper · explained in 1 episode
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Sim-to-Real Transfer — 5× in this paper · explained in 2 episodes
• Actor — 4× in this paper · explained in 3 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Split and Aggregate Policy Gradients — 3× in this paper
• Action Space — 2× in this paper · explained in 1 episode
• Failure Modes — 2× in this paper · explained in 3 episodes
• IEEE International Conference on Robotics and Automation — 2× in this paper
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Reward Function — 2× in this paper · explained in 2 episodes
• Reward Shaping — 2× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Imitation Learning (IL) — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation
• Open-TeleVision: Teleoperation with Immersive Active Visual Feedback
• AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
• Twisting Lids Off with Two Hands
• Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation
• FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning
• RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools
• MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
• Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation
• SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation
• OPEN TEACH: A Versatile Teleoperation System for Robotic Manipulation
• Holo-Dex: Teaching Dexterity with Immersive Mixed Reality
• DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System
• Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube
• DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies
• DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
• DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation
• Dexterous Functional Grasping
• End-to-end RL Improves Dexterous Grasping Policies
• DextrAH-RGB: Visuomotor Policies to Grasp Anything with Dexterous Hands

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving