Image de couverture de livre

Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Dongjie, Lei, Kun, Jiang, Zhennan, Pan, Jia, Xu, Huazhe
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning
par: Lei, Kun, et autres
Publié: (2025)

World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation
par: Jiang, Zhennan, et autres
Publié: (2025)

One-Policy-Fits-All: Geometry-Aware Action Latents for Cross-Embodiment Manipulation
par: Mu, Juncheng, et autres
Publié: (2026)

BiKC: Keypose-Conditioned Consistency Policy for Bimanual Robotic Manipulation
par: Yu, Dongjie, et autres
Publié: (2024)

Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
par: Li, Huanyu, et autres
Publié: (2026)

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
par: Lei, Kun, et autres
Publié: (2023)

Learning Visual Feature-Based World Models via Residual Latent Action
par: Zhang, Xinyu, et autres
Publié: (2026)

Steering Your Diffusion Policy with Latent Space Reinforcement Learning
par: Wagenmaker, Andrew, et autres
Publié: (2025)

Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations
par: Xu, Tengye, et autres
Publié: (2026)

Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning
par: Zhou, Huayi, et autres
Publié: (2026)

RFS: Reinforcement Learning with Residual Flow Steering for Dexterous Manipulation
par: Su, Entong, et autres
Publié: (2026)

BiKC+: Bimanual Hierarchical Imitation with Keypose-Conditioned Coordination-Aware Consistency Policies
par: Xu, Hang, et autres
Publié: (2026)

Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation
par: Ju, Yuanchen, et autres
Publié: (2024)

A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
par: Zhai, Shaopeng, et autres
Publié: (2025)

DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration
par: Guo, Lingxiao, et autres
Publié: (2025)

SViP: Sequencing Bimanual Visuomotor Policies with Object-Centric Motion Primitives
par: Chen, Yizhou, et autres
Publié: (2025)

CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation
par: Songwei, Wu, et autres
Publié: (2026)

Dexterous Grasping with Real-World Robotic Reinforcement Learning
par: Huang, Dongchi, et autres
Publié: (2025)

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
par: Wang, Yiqi, et autres
Publié: (2025)

Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation
par: Wu, Kun, et autres
Publié: (2024)

TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation
par: Xu, Qinwen, et autres
Publié: (2026)

Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids
par: Hu, Kaizhe, et autres
Publié: (2025)

Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation
par: Nagahisa, Haruto, et autres
Publié: (2026)

Efficient Real-World Autonomous Racing via Attenuated Residual Policy Optimization
par: Trumpp, Raphael, et autres
Publié: (2026)

Boosting Action-Information via a Variational Bottleneck on Unlabelled Robot Videos
par: Zhang, Haoyu, et autres
Publié: (2025)

DA-MMP: Learning Coordinated and Accurate Throwing with Dynamics-Aware Motion Manifold Primitives
par: Chu, Chi, et autres
Publié: (2025)

DittoGym: Learning to Control Soft Shape-Shifting Robots
par: Huang, Suning, et autres
Publié: (2024)

RoboDuet: Learning a Cooperative Policy for Whole-body Legged Loco-Manipulation
par: Pan, Guoping, et autres
Publié: (2024)

Learning Getting-Up Policies for Real-World Humanoid Robots
par: He, Xialin, et autres
Publié: (2025)

Sim-to-Real of Soft Robots with Learned Residual Physics
par: Gao, Junpeng, et autres
Publié: (2024)

Latent Policy Steering through One-Step Flow Policies
par: Im, Hokyun, et autres
Publié: (2026)

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
par: Chen, Zhongxi, et autres
Publié: (2026)

LongBench: Evaluating Robotic Manipulation Policies on Real-World Long-Horizon Tasks
par: Chen, Xueyao, et autres
Publié: (2026)

DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
par: Yang, Pengxuan, et autres
Publié: (2026)

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
par: Terence, Ng Wen Zheng, et autres
Publié: (2024)

ReSteer: Quantifying and Refining the Steerability of Multitask Robot Policies
par: Chen, Zhenyang, et autres
Publié: (2026)

Learning Visual Quadrupedal Loco-Manipulation from Demonstrations
par: He, Zhengmao, et autres
Publié: (2024)

Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation
par: Xiao, Junjin, et autres
Publié: (2026)

A Simulation Pipeline to Facilitate Real-World Robotic Reinforcement Learning Applications
par: Silveira, Jefferson, et autres
Publié: (2025)

RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking
par: Sun, Zhenguo, et autres
Publié: (2025)