X-Reset: Scaling Object-Centric Reinforcement Learning via Cross-Embodiment Resets

arXiv:2609.35715 · cs.LG, cs.AI, cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.LG, cs.AI, cs.RO

Submitted: 2026-09-28

Updated: 2026-09-28

Project page: https://xreset-applied.github.io/Abstract

Terminology

• Reinforcement Learning — 9× in this paper · explained in 4 episodes
• Generalization — 6× in this paper · explained in 13 episodes
• Actor — 5× in this paper · explained in 3 episodes
• In Conference on Robot Learning — 5× in this paper
• Conference on Computer Vision and Pattern Recognition — 4× in this paper
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• IEEE International Conference on Robotics and Automation — 4× in this paper
• Reward Function — 3× in this paper · explained in 2 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Inverse Kinematics — 2× in this paper
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Sim-to-Real Transfer — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Imitation Learning (IL) — 1× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 1× in this paper
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes

Sources

• Holo-Dex: Teaching Dexterity with Immersive Mixed Reality
• DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robots
• DexYCB: A Benchmark for Capturing Hand Grasping of Objects
• DexForce: Extracting Force-informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation
• Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes
• Object-Centric Dexterous Manipulation from Human Motion Data
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
• Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
• Reverse Curriculum Generation for Reinforcement Learning
• Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewards
• Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation
• EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
• OPEN TEACH: A Versatile Teleoperation System for Robotic Manipulation
• SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation
• PyRoki: A Modular Toolkit for Robot Kinematic Optimization
• Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation
• Phantom: Training Robots Without Robots Using Only Human Videos
• Masquerade: Learning from In-the-wild Human Videos using Data-Editing
• OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks