mlsanityData to 7 Oct 2026

Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations

arXiv 2003.06085 ↗First posted 13 Mar 2020cs.RO cs.AI cs.LGcited by 114

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

Abstract (arXiv)

Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to the lack of exploration, learning policies that generalize beyond the demonstrated behaviors is still an open challenge. We present a novel imitation learning framework to enable robots to 1) learn complex real world manipulation tasks efficiently from a small number of human demonstrations, and 2) synthesize new behaviors not contained in the collected demonstrations. Our key insight is that multi-task domains often present a latent structure, where demonstrated trajectories for different tasks intersect at common regions of the state space. We present Generalization Through Imitation (GTI), a two-stage offline imitation learning algorithm that exploits this intersecting structure to train goal-directed policies that generalize to unseen start and goal state combinations. In the first stage of GTI, we train a stochastic policy that leverages trajectory intersections to have the capacity to compose behaviors from different demonstration trajectories together. In the second stage of GTI, we collect a small set of rollouts from the unconditioned stochastic policy of the first stage, and train a goal-directed agent to generalize to novel start and goal configurations. We validate GTI in both simulated domains and a challenging long-horizon robotic manipulation domain in the real world. Additional results and videos are available at https://sites.google.com/view/gti2020/ .

Key facts. Cited by 114 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. First posted on arXiv 13 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 4; 2021: 8; 2022: 21; 2023: 21; 2024: 28; 2025: 20; 2026: 12.

114 papers.

Sort:

By area:

  1. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  2. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  3. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  4. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  5. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 229
  6. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 214
  7. 2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 160
  8. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 135
  9. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 117
  10. 2023Policy Representation via Diffusion Probability Model for Reinforcement Learningcited by 105
  11. 2024DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learningcited by 104
  12. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperationcited by 103
38 more
  1. 2022From Play to Policy: Conditional Behavior Generation from Uncurated Robot Datacited by 103
  2. 2022Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deploymentcited by 101
  3. 2021Learning by Watching: Physical Imitation of Manipulation Skills from Human Videoscited by 87
  4. 2020COG: Connecting New Skills to Past Experience with Offline Reinforcement Learningcited by 83
  5. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulationcited by 82
  6. 2022Latent Plans for Task-Agnostic Offline Reinforcement Learningcited by 81
  7. 2022BITS: Bi-level Imitation for Traffic Simulationcited by 80
  8. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 79
  9. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learningcited by 77
  10. 2023XSkill: Cross Embodiment Skill Discoverycited by 74
  11. 2022Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?cited by 70
  12. 2021Understanding Domain Randomization for Sim-to-real Transfercited by 69
  13. 2021A Workflow for Offline Model-Free Robotic Reinforcement Learningcited by 68
  14. 2024RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)cited by 68
  15. 2023Imitating Task and Motion Planning with Visuomotor Transformerscited by 63
  16. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 63
  17. 2024OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitationcited by 62
  18. 2023Learning Generalizable Manipulation Policies with Object-Centric 3D Representationscited by 60
  19. 2021Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulationcited by 59
  20. 2022Learning Neuro-Symbolic Skills for Bilevel Planningcited by 55
  21. 2022End-to-End Affordance Learning for Robotic Manipulationcited by 54
  22. 2022Skill-based Model-based Reinforcement Learningcited by 50
  23. 2022Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learningcited by 48
  24. 2024SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deploymentcited by 48
  25. 2024Vision-based Manipulation from Single Human Video with Open-World Object Graphscited by 46
  26. 2022MoCoDA: Model-based Counterfactual Data Augmentationcited by 44
  27. 2025Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulationcited by 42
  28. 2024CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Makingcited by 38
  29. 2023Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RLcited by 37
  30. 2024Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrationscited by 35
  31. 2023Human-in-the-Loop Task and Motion Planning for Imitation Learningcited by 28
  32. 2021Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Controlcited by 24
  33. 2024IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learningcited by 24
  34. 2023Universal Visual Decomposer: Long-Horizon Manipulation Made Easycited by 23
  35. 2022Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulationcited by 21
  36. 2022PATO: Policy Assisted TeleOperation for Scalable Robot Data Collectioncited by 19
  37. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  38. 2023Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challengescited by 17

50 most cited of 114 All 114 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning a Thousand Tasks in a Day
  2. 2021Towards More Generalizable One-shot Visual Imitation Learning
  3. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
  4. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning
  5. 2024Offline Imitation Learning Through Graph Search and Retrieval
  6. 2025Generalization Capability for Imitation Learning
  7. 2026Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation
  8. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement