A Model-Based Approach to Imitation Learning through Multi-Step Predictions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913799281311744 |
|---|---|
| author | Balim, Haldun Hu, Yang Zhang, Yuyang Li, Na |
| author_facet | Balim, Haldun Hu, Yang Zhang, Yuyang Li, Na |
| contents | Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent challenge of error correction and the distribution shift between training and deployment. In this paper, we present a novel model-based imitation learning framework inspired by model predictive control, which addresses these limitations by integrating predictive modeling through multi-step state predictions. Our method outperforms traditional behavior cloning numerical benchmarks, demonstrating superior robustness to distribution shift and measurement noise both in available data and during execution. Furthermore, we provide theoretical guarantees on the sample complexity and error bounds of our method, offering insights into its convergence properties. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13413 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Model-Based Approach to Imitation Learning through Multi-Step Predictions Balim, Haldun Hu, Yang Zhang, Yuyang Li, Na Machine Learning Robotics Systems and Control Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent challenge of error correction and the distribution shift between training and deployment. In this paper, we present a novel model-based imitation learning framework inspired by model predictive control, which addresses these limitations by integrating predictive modeling through multi-step state predictions. Our method outperforms traditional behavior cloning numerical benchmarks, demonstrating superior robustness to distribution shift and measurement noise both in available data and during execution. Furthermore, we provide theoretical guarantees on the sample complexity and error bounds of our method, offering insights into its convergence properties. |
| title | A Model-Based Approach to Imitation Learning through Multi-Step Predictions |
| topic | Machine Learning Robotics Systems and Control |
| url | https://arxiv.org/abs/2504.13413 |