mlsanityData to 7 Oct 2026

HYDRA: Hybrid Robot Actions for Imitation Learning

arXiv 2306.17237 ↗First posted 29 Jun 2023cs.ROcited by 54

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

Abstract (arXiv)

Imitation Learning (IL) is a sample efficient paradigm for robot learning using expert demonstrations. However, policies learned through IL suffer from state distribution shift at test time, due to compounding errors in action prediction which lead to previously unseen states. Choosing an action representation for the policy that minimizes this distribution shift is critical in imitation learning. Prior work propose using temporal action abstractions to reduce compounding errors, but they often sacrifice policy dexterity or require domain-specific knowledge. To address these trade-offs, we introduce HYDRA, a method that leverages a hybrid action space with two levels of action abstractions: sparse high-level waypoints and dense low-level actions. HYDRA dynamically switches between action abstractions at test time to enable both coarse and fine-grained control of a robot. In addition, HYDRA employs action relabeling to increase the consistency of actions in the dataset, further reducing distribution shift. HYDRA outperforms prior imitation learning methods by 30-40% on seven challenging simulation and real world environments, involving long-horizon tasks in the real world like making coffee and toasting bread. Videos are found on our website: https://tinyurl.com/3mc6793z

Key facts. Cited by 54 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 31 of its 40 references that are in the map. First posted on arXiv 29 Jun 2023.

Builds on

31 of 40 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Data Quality in Imitation Learning4 Jun
  2. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors20 Oct
  3. 2022Eliciting Compatible Demonstrations for Multi-Human Imitation Learning14 Oct
  4. 2021Learning Multi-Stage Tasks with One Demonstration via Self-Replay14 Nov
  5. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration13 May
  6. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperation12 Dec

Other references · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  7. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  8. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  9. 2017Hindsight Experience Replaycited by 1,096
  10. 2022A Generalist Agentcited by 802
  11. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  12. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
13 more
  1. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  2. 2021Implicit Behavioral Cloningcited by 442
  3. 2019Learning Latent Plans from Playcited by 310
  4. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 245
  5. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
  6. 2017DART: Noise Injection for Robust Imitation Learningcited by 187
  7. 2023Language-Driven Representation Learning for Roboticscited by 163
  8. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 98
  9. 2021Feedback in Imitation Learning: The Three Regimes of Covariate Shiftcited by 68
  10. 2019Uncertainty-Aware Data Aggregation for Deep Imitation Learningcited by 19
  11. 2022Learning Visuo-Haptic Skewering Strategies for Robot-Assisted Feedingcited by 15
  12. 2022PLATO: Predicting Latent Affordances Through Object-Centric Playcited by 12
  13. 2019Uncertainty-Aware Imitation Learning using Kernelized Movement Primitivescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 14; 2025: 17; 2026: 19.

54 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. 2024RT-H: Action Hierarchies Using Languagecited by 204
  8. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 176
  9. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 145
  10. 2024iVideoGPT: Interactive VideoGPTs are Scalable World Modelscited by 136
  11. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 108
  12. 2024IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AIcited by 68
38 more
  1. 2023Waypoint-Based Imitation Learning for Robotic Manipulationcited by 59
  2. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robotscited by 55
  3. 2023Imitation Bootstrapped Reinforcement Learningcited by 54
  4. 2026Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisonscited by 51
  5. 2025Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructionscited by 50
  6. 2024SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deploymentcited by 48
  7. 2024Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learningcited by 44
  8. 2024Diffusion Transformer Policycited by 41
  9. 2025Adversarial Attacks on Robotic Vision Language Action Modelscited by 31
  10. 2024Autoregressive Action Sequence Learning for Robotic Manipulationcited by 26
  11. 2025MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulationcited by 22
  12. 2025Dexterous Manipulation through Imitation Learning: A Surveycited by 18
  13. 2025XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representationscited by 15
  14. 2025TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Modelscited by 10
  15. 2025HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policiescited by 10
  16. 2026MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generationcited by 10
  17. 2025LatBot: Distilling Universal Latent Actions for Vision-Language-Action Modelscited by 7
  18. 2026LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoningcited by 7
  19. 2026RotVLA: Rotational Latent Action for Vision-Language-Action Modelcited by 7
  20. 2024PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learningcited by 6
  21. 2026Learning Additively Compositional Latent Actions for Embodied AIcited by 6
  22. 2026Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglementcited by 5
  23. 2026VIA: Visual Interface Agent for Robot Controlcited by 5
  24. 2025Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLAcited by 4
  25. 2026VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policiescited by 4
  26. 2024DIDA: Denoised Imitation Learning based on Domain Adaptationcited by 2
  27. 2025Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze Information and Motion Bottleneckscited by 2
  28. 2026STeP: Signal Temporal Logic for Precise Specifications for Action Generation with Vision Language Modelscited by 2
  29. 2026What Matters for Latent Actions in Robot Learningcited by 2
  30. 2025FABG : End-to-end Imitation Learning for Embodied Affective Human-Robot Interactioncited by 1
  31. 2025ACG: Action Coherence Guidance for Flow-based Vision-Language-Action modelscited by 1
  32. 2026WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systemscited by 1
  33. 2026TBD-VLA: Temporal Block Diffusion Vision Language Action Modelcited by 1
  34. 2025Prompt2Auto: From Motion Prompt to Automated Control via Geometry-Invariant One-Shot Gaussian Process Learningcited by 0
  35. 2025Hybrid Imitation Learning: Teleoperation Augmentation Primitives that Policies Learn to Triggercited by 0
  36. 2026Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulationcited by 0
  37. 2026Primitive Subspaces Mediate Few-Shot Transfer in VLAscited by 0
  38. 2026Improving Robotic Imitation Learning via Trajectory Standardizationcited by 0

50 most cited of 54 All 54 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections
  2. 2020Scalable Multi-Task Imitation Learning with Autonomous Improvement
  3. 2026Difference-Aware Retrieval Policies for Imitation Learning
  4. 2024Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames
  5. 2025Action Tokenizer Matters in In-Context Imitation Learning
  6. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learning
  7. 2025CCDP: Composition of Conditional Diffusion Policies with Guided Sampling
  8. 2026Hydra-0: Action Flow for Generalist World Modeling and Control