mlsanityData to 7 Oct 2026

Learning and Retrieval from Prior Data for Skill-based Imitation Learning

arXiv 2210.11435 ↗First posted 20 Oct 2022cs.LG cs.ROcited by 77

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Imitation learning offers a promising path for robots to learn general-purpose behaviors, but traditionally has exhibited limited scalability due to high data supervision requirements and brittle generalization. Inspired by recent advances in multi-task imitation learning, we investigate the use of prior data from previous tasks to facilitate learning novel tasks in a robust, data-efficient manner. To make effective use of the prior data, the robot must internalize knowledge from past experiences and contextualize this knowledge in novel tasks. To that end, we develop a skill-based imitation learning framework that extracts temporally extended sensorimotor skills from prior data and subsequently learns a policy for the target task that invokes these learned skills. We identify several key design choices that significantly improve performance on novel tasks, namely representation learning objectives to enable more predictable skill representations and a retrieval-based data augmentation mechanism to increase the scope of supervision for policy training. On a collection of simulated and real-world manipulation domains, we demonstrate that our method significantly outperforms existing imitation learning and offline reinforcement learning approaches. Videos and code are available at https://ut-austin-rpl.github.io/sailor

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 46 of its 58 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

46 of 58 references.

Closest ancestors · 7

Same direction, newest first

  1. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning4 Feb
  2. 2021Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation9 Dec
  3. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation28 Sep
  4. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperation12 Dec
  5. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations13 Mar
  6. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning25 Oct
  7. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation7 Nov

Other references · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  5. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  6. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
  7. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  8. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  9. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  10. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  11. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  12. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
27 more
  1. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  2. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  3. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  4. 2021Implicit Behavioral Cloningcited by 442
  5. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 342
  6. 2019Learning Latent Plans from Playcited by 310
  7. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  8. 2019RoboNet: Large-Scale Multi-Robot Learningcited by 268
  9. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  10. 2022Masked Visual Pre-training for Motor Controlcited by 246
  11. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 245
  12. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
  13. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 208
  14. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 164
  15. 2015Deep Spatial Autoencoders for Visuomotor Learningcited by 149
  16. 2019IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Datacited by 85
  17. 2020COG: Connecting New Skills to Past Experience with Offline Reinforcement Learningcited by 83
  18. 2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 73
  19. 2018TACO: Learning Task Decomposition via Temporal Alignment for Controlcited by 61
  20. 2022How to Leverage Unlabeled Data in Offline Reinforcement Learningcited by 61
  21. 2020Learning Robot Skills with Temporal Variational Inferencecited by 54
  22. 2017DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrationscited by 43
  23. 2021TRAIL: Near-Optimal Imitation Learning with Suboptimal Datacited by 39
  24. 2021Hierarchical Few-Shot Imitation with Skill Transition Modelscited by 37
  25. 2021LASER: Learning a Latent Action Space for Efficient Reinforcement Learningcited by 32
  26. 2021SKID RAW: Skill Discovery from Raw Trajectoriescited by 22
  27. 2022PLATO: Predicting Latent Affordances Through Object-Centric Playcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 21; 2025: 24; 2026: 21.

77 papers.

Sort:

By area:

  1. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  2. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  3. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  4. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  5. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  6. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  7. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  8. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 176
  9. 2024iVideoGPT: Interactive VideoGPTs are Scalable World Modelscited by 136
  10. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 108
  11. 2024DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learningcited by 104
  12. 2025Reinforcement Learning with Action Chunkingcited by 97
38 more
  1. 2023Data Quality in Imitation Learningcited by 72
  2. 2024IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AIcited by 68
  3. 2023Learning Generalizable Manipulation Policies with Object-Centric 3D Representationscited by 60
  4. 2025villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Modelscited by 58
  5. 2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasetscited by 56
  6. 2023Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperationcited by 49
  7. 2024SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deploymentcited by 48
  8. 2024Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learningcited by 44
  9. 2024STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learningcited by 42
  10. 2025Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulationcited by 42
  11. 2024Surgical Robot Transformer (SRT): Imitation Learning for Surgical Taskscited by 38
  12. 2024FlowRetrieval: Flow-Guided Data Retrieval for Few-Shot Imitation Learningcited by 32
  13. 2025DataMIL: Selecting Data for Robot Imitation Learning with Datamodelscited by 25
  14. 2025MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulationcited by 22
  15. 2023Accelerating Exploration with Unlabeled Prior Datacited by 21
  16. 2024Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directionscited by 20
  17. 2024Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptationcited by 19
  18. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  19. 2026LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfercited by 17
  20. 2025Curating Demonstrations using Online Experiencecited by 16
  21. 2025XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representationscited by 15
  22. 2024Leveraging Skills from Unlabeled Prior Data for Efficient Online Explorationcited by 13
  23. 2025Data Retrieval with Importance Weights for Few-Shot Imitation Learningcited by 10
  24. 2025TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Modelscited by 10
  25. 2025HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policiescited by 10
  26. 2025OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learningcited by 10
  27. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
  28. 2023PLEX: Making the Most of the Available Data for Robotic Manipulation Pretrainingcited by 9
  29. 2023NOIR: Neural Signal Operated Intelligent Robots for Everyday Activitiescited by 8
  30. 2024PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learningcited by 8
  31. 2026Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulationcited by 8
  32. 2024Robust Policy Learning via Offline Skill Diffusioncited by 7
  33. 2025LatBot: Distilling Universal Latent Actions for Vision-Language-Action Modelscited by 7
  34. 2026RotVLA: Rotational Latent Action for Vision-Language-Action Modelcited by 7
  35. 2023GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimationcited by 6
  36. 2026Hierarchical Latent Action Modelcited by 6
  37. 2026Learning Additively Compositional Latent Actions for Embodied AIcited by 6
  38. 2025COLLAGE: Adaptive Fusion-based Retrieval for Augmented Policy Learningcited by 5

50 most cited of 77 All 77 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement
  2. 2026Difference-Aware Retrieval Policies for Imitation Learning
  3. 2025Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
  4. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
  5. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections
  6. 2023Curriculum-Based Imitation of Versatile Skills
  7. 2022Imitation Learning by Estimating Expertise of Demonstrators
  8. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances