Robot Policy Learning

Ask about this topic

Overview

Robot policy learning studies how robots can turn camera, depth, tactile, and proprioceptive inputs into actions for tasks such as manipulation, locomotion, and navigation. Common approaches include behavior cloning from demonstrations, reinforcement learning in simulation or on hardware, and diffusion, flow-matching, or vision-language-action policies that generate action sequences; world models and hierarchical planners can add foresight and long-horizon structure. Researchers evaluate these methods in simulation suites such as LIBERO, CALVIN, RoboTwin, and navigation benchmarks, as well as on physical robots, with growing attention to memory, contact, safety, and recovery from failure. A central tension is how to make policies generalize across tasks, robots, and changing conditions while remaining data-efficient, reactive, reliable, and fast enough to deploy.

Latest papers

CardsList

377 papers85 papers in the last four weeks, up 47% on the four weeks before. 0.5% of all new papers.

  1. Gaussian Distillation of Flow Policies

    Oct 29, 2026Youssef Saied, Ziyad Sheebaelhamd, Claire Vernade +1Robot Policy LearningFlow-Based Policy Learning

    University of Geneva Geneva, Switzerland · University of Tübingen Tübingen, Germany · University of Technology Nuremberg Nuremberg, Germany +1

  2. Learning Safe Flow Matching Robot Policies from Binary Feasibility Oracles

    Oct 29, 2026Jianming Ma, Rongjun Jin, Yizhi Chen +1Robot Policy LearningSafe Robot Manipulation

    Shanghai Jiao Tong University · Tongji University

  3. Learning Event-based Obstacle Avoidance via Differentiable Simulation

    Oct 28, 2026Chenlu Shou, Yunfan Ren, Jiaxu Xing +1Collision AvoidanceQuadrotor Control

    Robotics and Perception Group, University of Zurich, Switzerland

  4. CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization

    Oct 28, 2026Zhiyuan Xiang, Xiang Deng, Wanjie Tao +3Robot Policy LearningRobot Skill Learning

    Harbin Institute of Technology (Shenzhen) · Mashang Consumer Finance Co., Ltd. · Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China

  5. Same Label, Different Interface: Beyond Action-Space Labels in Robot Learning

    Oct 28, 2026Arshia Sangwan, Zhongyang ZhangRobot Policy LearningRobotic Control

    New York University · University of California San Diego

  6. Learning Quality-Controllable Robot Policies with Iterative Hindsight Relabeling

    Oct 27, 2026Sinjae Kang, Dong Kyu Shin, Jaehong Kim +6Robot Policy LearningRobotic Manipulation

    KAIST · LGE · Microsoft Research +1

  7. A Trainable CPG Framework for Quadruped Locomotion

    Oct 27, 2026Xiyan Liu, Yide Liu, Guoyong Mao +1Robot LocomotionQuadruped Locomotion

    The authors are with the State Key Laboratory of Fluid Power & Mechatronic Systems, Key Laboratory of Soft Machines and Smart Devices of Zhejiang Province, Center for X-Mechanics, Department of Engineering Mechanics, Zhejiang University, 38 Zheda Road, Hangzhou 310027, China.

  8. Rollback: Experience Backtracking in World Models for Policy Improvement

    Oct 26, 2026Jiayi Luo, Yang Zhang, Liliang Chen +13Robot Policy LearningRobotic RL

    AgiBot · BUAA · NUS

  9. Differentiable Contact Dynamics for Legged Locomotion: Policy Learning and Contact-Implicit Trajectory Optimization

    Oct 26, 2026Gijeong Kim, Seungbin Oh, Dongyun Kang +1Differentiable PhysicsTrajectory Optimization

    The authors are with the Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, South Korea.

  10. Learning Direct Control from Optimization for Dynamic Target Tracking

    Oct 26, 2026Bing Sun, Yue Lin, Canhui Wen +4Robot Policy LearningNeural Network Control

  11. Behavioural Quality Is Not Learning Utility: Objective Mismatch in Human Behaviour Models for Robot Learning

    Oct 26, 2026Haoyang Jiang, Dana Kulic, Michael Burke +1Human Behavior ModelingHuman Behavior Simulation

    Department of Electrical and Computer Systems Engineering, Monash University, Clayton, Australia

  12. AdaPolicy: Action-Driven Anticipatory Robot Policies via Next-Chunk Prediction

    Oct 25, 2026Fan Yang, Yuting Su, Chen Zhao +2Robot Policy LearningNext-Action Prediction

    Tianjin University · University of Bologna

  13. ElevateHead: Decide Once, Then Commit: When the Action Head Matters for Multimodal Imitation

    Oct 25, 2026Tsung-Lung YangRobot Policy LearningImitation Learning

    National University

  14. Tiny Recursive Policy: Recursive Latent Refinement for Visuomotor Control

    Oct 23, 2026Hakan Aktas, Cengiz OztireliRobot Policy LearningVisuomotor Policy Learning

    University of Cambridge, Cambridge, United Kingdom

  15. Retiming Robot Demonstrations with a Learned Speed Prior

    Oct 23, 2026Seungyong Moon, Deokjae Lee, Hansang Lee +7Robot Policy LearningLearning from Demonstration

    Seoul National University

  16. Asymmetric On-Policy Distillation Learns In-Context Exploration

    Oct 21, 2026Sriyash Poddar, Yanda Bao, Jacob Krantz +5RL ExplorationPartially Observable RL

    Paul G. Allen School of Computer Science and Engineering, University of Washington · Work partially done while at Meta

  17. AirPlayground: Benchmarking Aerial Navigation across Diverse Reconstructed Environments

    Oct 21, 2026Rangya Zhang, Yujing Shang, Zhuoyuan Yu +5UAV NavigationRobot Navigation Benchmarks

    Nanyang Technological University · Wuhan University · Nanjing University of Aeronautics and Astronautics

  18. GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models

    Oct 20, 2026Ziyong Wang, Yupei Lin, Runxuan Huang +3Tactile-Vision-Language-Action ModelsRobot Policy Learning

    Sun Yat-sen University · X-Era AI Lab · The Hong Kong Polytechnic University

  19. AWLS: Advantage-Weighted Latent Steering for One-Step Generative Robotic Manipulation Policies

    Oct 20, 2026Jiahong Tang, Jiaju He, Zhiyuan Yang +2Robot Policy LearningRobotic Manipulation

    Nanyang Technological University, Singapore · Singapore Institute of Manufacturing Technology (SIMTech), Agency for Science, Technology and Research (A*STAR), Singapore

  20. Learning from Fleet Experience: Collective Experience Learning Across 96 Robots

    Oct 19, 2026Chao Yu, Shu'ang Yu, Hao Lin +41Robot Policy LearningRobot Learning

  21. Escape Without a Recipe: Maneuver-Agnostic Mars Rover Recovery from Granular Entrapment

    Oct 17, 2026Meraj Hossain Promit, Chandak Chakma, Md Jubair Ahmed Sourov +1Planetary Rover RoboticsRobot Failure Recovery

    Department of Robotics & Mechatronics Engineering, University of Dhaka, Bangladesh. · Department of AI & Robotics, New Uzbekistan University, Uzbekistan.

  22. Learning Robot Metareasoning: Adaptive Computation Budgets for Real-Time Control

    Oct 16, 2026Lorenzo Magnino, Antonio Marino, Michael Amir +2Real-Time Robot ControlRobotic Control

    University of Cambridge — Cambridge, United Kingdom. · College of Engineering and Computing at George Mason University

  23. TransNav: Transformer-Based End-to-End Navigation Method for Static and Dynamic Quadrotor Obstacle Avoidance

    Oct 16, 2026Jianghan Zhu, Zhuo Li, Yanjun Zhang +1Robot NavigationAerial Robotics

    The authors are with the State Key Laboratory of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing 100081, China

  24. Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors

    Oct 16, 2026Carl Qi, Weijun Dong, Xiaojie Wang +8Robot Policy LearningRobotic RL

    Amazon · UT Austin · UC San Diego +2

  25. CoDA: Co-Evolution of Data Engines and Action Policies

    Oct 15, 2026Tianjiao Yu, Zhilin Ou, Yifan Shen +5Robot Policy LearningSynthetic Data Generation for Robotics

    University of Illinois Urbana-Champaign · The Chinese University of Hong Kong, Shenzhen · Amazon

  26. MOSS: Mode-Oriented Source Shaping for Robot Flow Matching Policies

    Oct 15, 2026Zirun Ma, Jindou Jia, Tuo An +3Robot Policy LearningRobotic Manipulation

    MARS Lab, Nanyang Technological University · Tsinghua University

  27. Physical Time as a Missing Dimension of Robot Policy Memory Dynamics

    Oct 14, 2026Yushen Liang, Yue Peng, Baosheng Jin +6Robot Policy LearningMemory-Augmented Agents

    New York University Shanghai, Shanghai, China · University of Electronic Science and Technology of China, Chengdu, China

  28. When Do Discrete Actions Make Good Continuous Controllers?

    Oct 14, 2026Zeji Yi, Soham Dasgupta, Xinyang Zhang +5Robot Policy LearningVLMs for Robotics

    Carnegie Mellon University · Amazon FAR (Frontier AI & Robotics)

  29. Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation

    Oct 14, 2026Hanlin Liu, Zichen Zhou, Jiacheng Zhang +6Robot Policy LearningRobotic Manipulation

    The Hong Kong University of Science and Technology (Guangzhou) · Beijing Institute of Technology · Shanghai Jiao Tong University +2

  30. ACRO: Actor-Critic Rollout Orchestration

    Oct 14, 2026Junhoo Lee, Seungyeon Kim, Baekseung Kim +4Robotic ManipulationRobot Policy Learning

    Korea Advanced Institute of Science and Technology (KAIST) · Seoul National University