mlsanityData to 7 Oct 2026

PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning

arXiv 2403.00929 ↗First posted 1 Mar 2024cs.RO cs.AI cs.LGcited by 8

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

Abstract (arXiv)

Imitation learning has shown great potential for enabling robots to acquire complex manipulation behaviors. However, these algorithms suffer from high sample complexity in long-horizon tasks, where compounding errors accumulate over the task horizons. We present PRIME (PRimitive-based IMitation with data Efficiency), a behavior primitive-based framework designed for improving the data efficiency of imitation learning. PRIME scaffolds robot tasks by decomposing task demonstrations into primitive sequences, followed by learning a high-level control policy to sequence primitives through imitation learning. Our experiments demonstrate that PRIME achieves a significant performance improvement in multi-stage manipulation tasks, with 10-34% higher success rates in simulation over state-of-the-art baselines and 20-48% on physical hardware.

Key facts. Cited by 8 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 43 of its 61 references that are in the map. First posted on arXiv 1 Mar 2024.

Builds on

43 of 61 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023Waypoint-Based Imitation Learning for Robotic Manipulation26 Jul
  2. 2023Multi-Stage Cable Routing through Hierarchical Imitation Learning18 Jul
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware23 Apr
  4. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Play24 Feb
  5. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learning20 Oct
  6. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors20 Oct
  7. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation28 Sep
  8. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations13 Mar

Other references · 35

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  2. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  3. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  4. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  5. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  6. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  7. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  8. 2019Learning Latent Plans from Playcited by 310
  9. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  10. 2020Integrated Task and Motion Planningcited by 281
  11. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
  12. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
23 more
  1. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
  2. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 208
  3. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 164
  4. 2020Parrot: Data-Driven Behavioral Priors for Reinforcement Learningcited by 136
  5. 2013Data-Driven Grasp Synthesis - A Surveycited by 104
  6. 2019IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Datacited by 85
  7. 2022Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trialscited by 78
  8. 2021Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Taskscited by 75
  9. 2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 73
  10. 2015Deep Reinforcement Learning in Parameterized Action Spacecited by 65
  11. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 63
  12. 2015Reinforcement Learning with Parameterized Actionscited by 61
  13. 2018TACO: Learning Task Decomposition via Temporal Alignment for Controlcited by 61
  14. 2022How to Leverage Unlabeled Data in Offline Reinforcement Learningcited by 61
  15. 2018Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstrationcited by 60
  16. 2020Learning Robot Skills with Temporal Variational Inferencecited by 54
  17. 2019Efficient Bimanual Manipulation Using Learned Task Schemascited by 44
  18. 2017DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrationscited by 43
  19. 2020Planning from Pixels using Inverse Dynamics Modelscited by 36
  20. 2023Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitationcited by 30
  21. 2022Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectoriescited by 27
  22. 2019RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstrationcited by 19
  23. 2023Predicting Object Interactions with Behavior Primitives: An Application in Stowing Taskscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 2.

8 papers.

  1. 2025Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulationcited by 15
  2. 2025Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulationcited by 13
  3. 2025MTIL: Encoding Full History with Mamba for Temporal Imitation Learningcited by 10
  4. 2024DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignmentcited by 7
  5. 2025ViSA-Flow: Accelerating Robot Skill Learning via Large-Scale Video Semantic Action Flowcited by 5
  6. 2026Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervisioncited by 2
  7. 2025Hybrid Imitation Learning: Teleoperation Augmentation Primitives that Policies Learn to Triggercited by 0
  8. 2026RAPID: Robot Agentic Programming from Demonstrationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation
  2. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration
  3. 2020PICO: Primitive Imitation for COntrol ↗
  4. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environments
  5. 2025Learning a Thousand Tasks in a Day
  6. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
  7. 2025Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges
  8. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections