Self-Evolved Imitation Learning in Simulated World
- 13 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (6) , 6967-6974
Abstract
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 tasks in 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 code is available at https://github.com/Jasper-aaa/SEIL.git.Keywords
All Related Versions
Funding Information
- Research Computing Core Group Office of the Vice President for Research
- Hamad Bin Khalifa University
This publication has 18 references indexed in Scilit:
- VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation2025
- Revolutionizing surgery: AI and robotics for precision, risk reduction, and innovationJournal of Robotic Surgery, 2025
- Diffusion policy: Visuomotor policy learning via action diffusionThe International Journal of Robotics Research, 2024
- Task Residual for Tuning Vision-Language Models2023
- DROPO: Sim-to-real transfer with offline domain randomizationRobotics and Autonomous Systems, 2023
- Reinforcement learning building control approach harnessing imitation learningEnergy and AI, 2023
- Offline Meta-Reinforcement Learning for Industrial Insertion2022
- How to train your robot with deep reinforcement learning: lessons we have learnedThe International Journal of Robotics Research, 2021
- Deep Reinforcement Learning: A Brief SurveyIEEE Signal Processing Magazine, 2017
- Deep Residual Learning for Image Recognition2016