mlsanityData to 14 Oct 2026

Self-evolved Imitation Learning in Simulated World

arXiv 2509.19460 ↗First posted 23 Sep 2025cs.RO cs.AI cs.LGcited by 4

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

Abstract (arXiv)

Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited supervision, we propose Self-Evolved Imitation Learning (SEIL), a framework that progressively improves a few-shot model through simulator interactions. The model first attempts tasksin the simulator, from which successful trajectories are collected as new demonstrations for iterative refinement. To enhance the diversity of these demonstrations, SEIL employs dual-level augmentation: (i) Model-level, using an Exponential Moving Average (EMA) model to collaborate with the primary model, and (ii) Environment-level, introducing slight variations in initial object positions. We further introduce a lightweight selector that filters complementary and informative trajectories from the generated pool to ensure demonstration quality. These curated samples enable the model to achieve competitive performance with far fewer training examples. Extensive experiments on the LIBERO benchmark show that SEIL achieves a new state-of-the-art performance in few-shot imitation learning scenarios. Code is available at https://github.com/Jasper-aaa/SEIL.git.

Key facts. Cited by 4 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 25 of its 33 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

25 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations30 Mar
  2. 2021Implicit Behavioral Cloning1 Sep

Other references · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Deep reinforcement learning from human preferencescited by 3,912
  3. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  4. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  5. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  6. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  7. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
  8. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 367
  9. 2022Behavior Transformers: Cloning k modes with one stonecited by 304
  10. 2021Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimismcited by 279
  11. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
  12. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 177
11 more
  1. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 169
  2. 2023Open-World Object Manipulation using Pre-trained Vision-Language Modelscited by 156
  3. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 145
  4. 2022Task Residual for Tuning Vision-Language Modelscited by 123
  5. 2024BAKU: An Efficient Transformer for Multi-Task Policy Learningcited by 80
  6. 2023GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graphcited by 69
  7. 2024QueST: Self-Supervised Skill Abstractions for Learning Continuous Controlcited by 53
  8. 2025VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulationcited by 46
  9. 2021Offline Meta-Reinforcement Learning for Industrial Insertioncited by 39
  10. 2022DROPO: Sim-to-Real Transfer with Offline Domain Randomizationcited by 19
  11. 2022Implicit Offline Reinforcement Learning via Supervised Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025SimScale: Learning to Drive via Real-World Simulation at Scalecited by 36
  2. 2026Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulationcited by 19
  3. 2026NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Modelscited by 2
  4. 2026DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imaginationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Imitation Learning: Progress, Taxonomies and Challenges
  2. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  3. 2024A Survey of Imitation Learning Methods, Environments and Metrics
  4. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
  5. 2022Diverse Imitation Learning via Self-Organizing Generative Models
  6. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges
  7. 2020ADAIL: Adaptive Adversarial Imitation Learning
  8. 2023Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrations