mlsanityData to 14 Oct 2026

X-IL: Exploring the Design Space of Imitation Learning Policies

arXiv 2502.12330 ↗First posted 17 Feb 2025cs.RO cs.LGcited by 10

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Designing modern imitation learning (IL) policies requires making numerous decisions, including the selection of feature encoding, architecture, policy representation, and more. As the field rapidly advances, the range of available options continues to grow, creating a vast and largely unexplored design space for IL policies. In this work, we present X-IL, an accessible open-source framework designed to systematically explore this design space. The framework's modular design enables seamless swapping of policy components, such as backbones (e.g., Transformer, Mamba, xLSTM) and policy optimization techniques (e.g., Score-matching, Flow-matching). This flexibility facilitates comprehensive experimentation and has led to the discovery of novel policy configurations that outperform existing methods on recent robot learning benchmarks. Our experiments demonstrate not only significant performance gains but also provide valuable insights into the strengths and weaknesses of various design choices. This study serves as both a practical reference for practitioners and a foundation for guiding future research in imitation learning.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 47 of its 59 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

47 of 59 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022imitation: Clean Imitation Learning Implementations22 Nov
  2. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  3. 2018Behavioral Cloning from Observation4 May

Other references · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2022Flow Matching for Generative Modelingcited by 5,702
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  9. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  10. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  11. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  12. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
32 more
  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  3. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  6. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  7. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
  8. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 622
  9. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 407
  10. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 349
  11. 2019Learning Latent Plans from Playcited by 316
  12. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  13. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 282
  14. 2023Imitating Human Behaviour with Diffusion Modelscited by 263
  15. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 236
  16. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 209
  17. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 169
  18. 2024Behavior Generation with Latent Actionscited by 160
  19. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 138
  20. 2020Language-Conditioned Imitation Learning for Robot Manipulation Taskscited by 136
  21. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 134
  22. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representationscited by 116
  23. 2020Visual Imitation Made Easycited by 111
  24. 2024What Matters in Building Vision-Language-Action Models for Generalist Robotscited by 89
  25. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 67
  26. 2024Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learningcited by 48
  27. 2024CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Makingcited by 39
  28. 2024Flow Matching Imitation Learning for Multi-Support Manipulationcited by 29
  29. 2022FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulationcited by 24
  30. 2022Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Taskscited by 17
  31. 2021Data-driven approaches for predicting spread of infectious diseases through DINNs: Disease Informed Neural Networkscited by 15
  32. 2022TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speedcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 7.

10 papers.

  1. 2026ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Modelcited by 13
  2. 2025MTIL: Encoding Full History with Mamba for Temporal Imitation Learningcited by 10
  3. 2025PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learningcited by 10
  4. 2025Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learningcited by 9
  5. 2026VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memorycited by 6
  6. 2026Expert Behavior Prior Reinforcement Learningcited by 0
  7. 2026Mamba-based Selective State Space Modeling Improves the Accuracy-Complexity Tradeoff of SmolVLA Vision-Language-Action Expertscited by 0
  8. 2026Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speedscited by 0
  9. 2026SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persistscited by 0
  10. 2026UniLAP: A Unified Latent Action Policy for Cross-Embodiment Manipulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026To Do or Not to Do: Ensuring the Safety of Visuomotor Policies Learned from Demonstrations
  2. 2022Interactive Imitation Learning in Robotics: A Survey
  3. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges
  4. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  5. 2026When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
  6. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
  7. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learning
  8. 2021A Pragmatic Look at Deep Imitation Learning