Cover Image

SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Yang, Lv, Jun, Xue, Han, Chen, Wendi, Wen, Chuan, Lu, Cewu
Format:	Preprint
Published:	2025
Subjects:	Robotics Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SIME: Enhancing Policy Self-Improvement with Modal-level Exploration
by: Jin, Yang, et al.
Published: (2025)

RoboPocket: Improve Robot Policies Instantly with Your Phone
by: Fang, Junjie, et al.
Published: (2026)

ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning
by: Chen, Wendi, et al.
Published: (2025)

DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment
by: Chen, Wendi, et al.
Published: (2024)

Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation
by: Xue, Han, et al.
Published: (2025)

DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model
by: Jin, Yang, et al.
Published: (2024)

FP3: A 3D Foundation Policy for Robotic Manipulation
by: Yang, Rujia, et al.
Published: (2025)

Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration
by: Kantaros, Yiannis, et al.
Published: (2024)

Energy-Efficient SLAM via Joint Design of Sensing, Communication, and Exploration Speed
by: Han, Zidong, et al.
Published: (2024)

Rethinking Camera Choice: An Empirical Study on Fisheye Camera Properties in Robotic Manipulation
by: Xue, Han, et al.
Published: (2026)

Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
by: Pappalardo, Octavio
Published: (2026)

Optimizing TD3 for 7-DOF Robotic Arm Grasping: Overcoming Suboptimality with Exploration-Enhanced Contrastive Learning
by: Hsieh, Wen-Han, et al.
Published: (2024)

Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation
by: Patel, Bhrij, et al.
Published: (2023)

UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
by: Zhang, Jianke, et al.
Published: (2025)

MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation
by: von Hartz, Jan Ole, et al.
Published: (2025)

Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition
by: Luo, Shengcheng, et al.
Published: (2024)

LLM-based Human-like Traffic Simulation for Self-driving Tests
by: Li, Wendi, et al.
Published: (2025)

TieBot: Learning to Knot a Tie from Visual Demonstration through a Real-to-Sim-to-Real Approach
by: Peng, Weikun, et al.
Published: (2024)

Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs
by: Tang, Wenjing, et al.
Published: (2025)

Digital Gene: Learning about the Physical World through Analytic Concepts
by: Sun, Jianhua, et al.
Published: (2025)

ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation
by: Lu, Guanxing, et al.
Published: (2024)

Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision
by: Oh, Hanbit, et al.
Published: (2025)

Safe Exploration via Policy Priors
by: Wendl, Manuel, et al.
Published: (2026)

RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation
by: Xue, Yuquan, et al.
Published: (2025)

Human-assisted Robotic Policy Refinement via Action Preference Optimization
by: Xia, Wenke, et al.
Published: (2025)

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency
by: Su, Yifei, et al.
Published: (2025)

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
by: Luo, Jianlan, et al.
Published: (2024)

Sample-Efficient Reinforcement Learning with Symmetry-Guided Demonstrations for Robotic Manipulation
by: Enayati, Amir M. Soufi, et al.
Published: (2023)

Human-in-the-loop Online Rejection Sampling for Robotic Manipulation
by: Lu, Guanxing, et al.
Published: (2025)

ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation
by: Yu, Wenye, et al.
Published: (2025)

IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation
by: Rana, Krishan, et al.
Published: (2025)

Vision-Language-Policy Model for Dynamic Robot Task Planning
by: Wang, Jin, et al.
Published: (2025)

Efficient Continual Adaptation of Pretrained Robotic Policy with Online Meta-Learned Adapters
by: Zhu, Ruiqi, et al.
Published: (2025)

Contextual Affordances for Safe Exploration in Robotic Scenarios
by: Ye, William Z., et al.
Published: (2024)

Learning Soft Robotic Dynamics with Active Exploration
by: Zheng, Hehui, et al.
Published: (2025)

Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
by: Chen, Yanzhe, et al.
Published: (2026)

EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots
by: Lei, Zixing, et al.
Published: (2026)

Learning the Generalizable Manipulation Skills on Soft-body Tasks via Guided Self-attention Behavior Cloning Policy
by: Li, Xuetao, et al.
Published: (2024)

One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies
by: Li, Shaolong, et al.
Published: (2026)

Executable Analytic Concepts as the Missing Link Between VLM Insight and Precise Manipulation
by: Sun, Mingyang, et al.
Published: (2025)