Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Balim, Haldun, Hu, Yang, Zhang, Yuyang, Li, Na
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979252262
Cites:
Cited by:
Related to: