Robot Imitation Learning

Follow this topic Ask about this topic

Latest papers 647

172 papers in the last four weeks, up 310% on the four weeks before. 1.0% of all new papers.

All topics

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
Jun 1, 2026Christian Scherer, Joe Watson, Theo Gruner +3Reinforcement Learning Robot Skill Learning
Technical University of Darmstadt · Zuse School ELIZA · University of Oxford +2
Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
Jun 1, 2026Shoya Kuno, Yumo Ouchi, Kanata SuzukiMobile Robotics Robot Navigation
Spatial Robotics Research Center, Fujitsu Limited., Kanagawa 211-8588, Japan.
Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections
Jun 1, 2026Zhaoting Li, Gang Chen, Javier Alonso-Mora +2Diffusion Policy Robotic Manipulation
Delft University of Technology · University of Stuttgart
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
May 31, 2026Zemin Yang, Yaoyu He, Yiming Zhong +5Robot Policy Learning Imitation Learning
ShanghaiTech University · Shanghai Jiao Tong University · The Chinese University of Hong Kong +1
Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs
May 31, 2026Jianing Qian, Qinhe Peng, Emmanuel Panov +4Long-Horizon Robotic Manipulation Imitation Learning
University of Pennsylvania · RAI Institute · University of Michigan
HOIST: Humanoid Optimization with Imitation and Sample-efficient Tuning for Manipulating Suspended Loads
May 29, 2026Songyang Liu, Shunyu Yao, Dingyuan Huang +1RL for Robotics Humanoid Robot Control
Department of Civil and Coastal Engineering University of Florida United States
Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills
May 29, 2026Shuai Ke, Jiexin Zhang, Huan Zhao +4Contact-Rich Robotic Manipulation Diffusion Policy
State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
MARS Policy: Multimodality Only When It Matters
May 28, 2026Jindou Jia, Tuo An, Yuxuan Hu +7Efficient Multimodal Inference Robot Policy Learning
1MARS Lab, Nanyang Technological University
Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation
May 28, 2026Dayuan Chen, Kai Tang, Yukuan Zhang +2Bimanual Robotic Manipulation Deformable Object Manipulation
Department of Robotics, Tohoku University, Sendai, Miyagi, Japan · JC STEM Lab of Robotics for Soft Materials, the Department of Electrical and Computer Engineering, Faculty of Engineering, The University of Hong Kong, Hong Kong SAR, China
MonoDuo: Using One Robot Arm to Learn Bimanual Policies
May 28, 2026Sandeep Bajamahal, Lawrence Yunliang Chen, Toru Lin +3Bimanual Robotic Manipulation Cross-Embodiment Robot Learning
University of California, Berkeley
Imitation Learning for Robot Assistance in Open Surgery: A Multi-Policy Evaluation on Suture Following
May 27, 2026Xucheng Wang, Zhizhou Yang, Xiaoman Zhang +3Visuomotor Policy Learning Robot Imitation Learning
Department of Biomedical Informatics, Harvard Medical School, Boston, MA · Department of Surgery, Massachusetts General Hospital, Boston, MA
Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation Learning
May 27, 2026Meraj Mammadov, Pedro Zuidberg Dos Martires, Johannes Andreas StorkImitation Learning Robot Imitation Learning
Department of Computer Science Örebro University
ProgVLA: Progress-Aware Robot Manipulation Skill Learning
May 27, 2026Seungsu Kim, Jinyoung Choi, Seungmin Baek +1Cross-Modal Learning Efficient Multimodal Inference
NAVER LABS Europe · NAVER LABS
How Should We Teach Robots? A Comparison of Kinesthetic, Joystick, and Gesture-Based Teaching
May 27, 2026Petr Vanc, Jan Kristof Behrens, Václav Hlaváč +1Robot Teleoperation Robotic Manipulation
Czech Institute of Informatics, Robotics and Cybernetics (CIIRC CTU) Jugoslávských partyzánů 1580/3, 160 00 Dejvice
Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal
May 27, 2026Junlin WangDiffusion Model Guidance Diffusion Guidance
School of Engineering and Applied Science University of Pennsylvania
VR-DAgger: Immersive VR for Dexterous Data Collection and Uncertainty-Guided On-Policy Correction
May 26, 2026René Zurbrügg, Tifanny Portela, Arjun Bhardwaj +3Robotic Data Collection Robot Teleoperation
The Authors are with the Robotics Systems Lab ETH Zürich.
Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming
May 26, 2026Oleh Borys, Karla StepanovaRobot Skill Learning Robotic Manipulation
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague.
On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning
May 26, 2026Thomas Lips, Marco Moletta, Michael C. Welle +2Generalization in Robotic Manipulation Imitation Learning
AI and Robotics Lab, IDLAB-AIRO, Ghent University-imec · Robotics, Perception and Learning Lab, (RPL), EECS, KTH Royal Institute of Technology. · INCAR Robotics AB, Stockholm, Sweden.
How to Mitigate the Distribution Shift Problem in Robotics Control: A Robust and Adaptive Approach Based on Offline to Online Imitation Learning
May 25, 2026Hyung-Suk Yoon, Seung-Woo SeoDistribution Shift Robustness Imitation Learning
Department of Electronic and Computer Engineering, Seoul National University, Seoul, South Korea.
HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos
May 24, 2026Zhi Wang, Botao He, Kelin Yu +4Zero-Shot Learning Zero-Shot Robotic Manipulation
University of Maryland
Learning Transferable Motor Skills for Geometry-Aware Robotic Surface Tasks
May 24, 2026Miroslav David, Karla Stepanova, Robert BabuskaRobot Skill Learning Robot Motion Generation
Department of Robotics and Machine Perception, Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Czech Republic. · Cognitive Robotics, Faculty of 3mE, Delft University of Technology, The Netherlands.
MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
May 23, 2026Yusen Feng, Xiang Wang, Heyuan Yao +7Latent Action Learning Humanoid Robot Locomotion
Peking University
RoboHitch: Learning Visual Affordance from Disordered Keypoints for Hitch Knots Tying
May 23, 2026Jiahui Zuo, Boyang Zhang, Fumin ZhangDeformable Object Manipulation Robotic Manipulation
Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong
Instrumentation for Imitation Learning: Enhancing Training Datasets for Clothes Hanger Insertion
May 22, 2026Remko Proesmans, Thomas Lips, Francis wyffelsRobot Skill Learning Robotic Insertion
AI and Robotics Lab (IDLab-AIRO), Ghent University—imec, Ghent, Belgium
Direct Dynamic Retargeting for Humanoid Imitation Learning from Videos
May 22, 2026Constant Roux, Ludovic De Matteïs, Armand Jordana +4Humanoid Robot Control Motion Retargeting
LAAS-CNRS, Université de Toulouse, CNRS, Toulouse, France · IRT Saint-Exupéry, Toulouse, France · Artificial and Natural Intelligence Toulouse Institute (ANITI), Toulouse, France
SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control
May 21, 2026Jingyan Zhang, Han Liang, Ruichi Zhang +6RL for Robotics Humanoid Robot Control
ShanghaiTech University, China · Bytedance Seed, China · University of Pennsylvania, USA +2
PGDG: Physically Grounded Data Generation for Robust Bimanual Policy Learning from a Single Demonstration
May 20, 2026Cunxi Dai, Haoran Chang, Aditya Nisal +5Robot Policy Learning Bimanual Robotic Manipulation
Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Dexmate, USA
Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulation
May 20, 2026Haoran Huang, Haonan Dong, Huixu DongLong-Horizon Robotic Manipulation Mobile Manipulation
Zhejiang University, Hangzhou 310027, China
Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
May 20, 2026Jingyang He, Guangrun Li, Jieyu Zhang +3Robot Skill Learning World Models for Robotics
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Innovation Center of Humanoid Robotics · University of Washington
Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
May 20, 2026Benedict Quartey, Sebastian Castro, Eric Rosen +3Robot Skill Learning Generalization in Robotic Manipulation
Brown University · Robotics & AI Institute

Jun 1, 2026J/K move · Enter open · S save

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek+2

Technical University of Darmstadt · Zuse School ELIZA · University of Oxford+2

Reinforcement Learning Robot Skill Learning Imitation Learning Robot Imitation Learning Sparse-Reward RL RL Fine-Tuning+2

Open paper AskPDF arXiv

Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more human demonstrations. Prior work has finetuned large pretrained policies in a scalable fashion by applying RL to a smaller residual policy that corrects the pretrained model. However, for the typical sparse reward tasks, RL algorithms can struggle to optimize the behavior in a sample-efficient manner. We explore inverse reinforcement learning, where a dense reward function is learned from expert demonstrations, potentially reducing the challenge of RL finetuning. We specifically consider coherent imitation learning, an IRL method that facilitates improvement of the BC policy through using a specific reward formulation with theoretical guarantees. We show that our IRL method maintains or improves the performance of pi-0.5 on all six sparse manipulation tasks and achieves a

\geq 90\%

success rate on five out of six complex manipulation tasks, outperforming RL-based baselines using sparse rewards. By ensuring our initial pretrained finetuning policy is optimal for our initial reward and critic, our method circumvents the initial drop commonly seen in RL finetuning and enables faster improvement.