mlsanityData to 7 Oct 2026

A Model-Based Approach to Imitation Learning through Multi-Step Predictions

arXiv 2504.13413 ↗First posted 18 Apr 2025cs.LG cs.RO cs.SYcited by 0

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

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 8 of its 20 references that are in the map. First posted on arXiv 18 Apr 2025.

Builds on

8 of 20 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning20 Jul
  2. 2024DIDA: Denoised Imitation Learning based on Domain Adaptation4 Apr
  3. 2022TaSIL: Taylor Series Imitation Learning30 May
  4. 2018An Algorithmic Perspective on Imitation Learning16 Nov

Other references · 4

  1. 2016Generative Adversarial Imitation Learningcited by 1,576
  2. 2017DART: Noise Injection for Robust Imitation Learningcited by 187
  3. 2022Model-Based Imitation Learning for Urban Drivingcited by 149
  4. 2023Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behaviorcited by 33

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Model Predictive Control via On-Policy Imitation Learning
  2. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  3. 2018Accelerating Imitation Learning with Predictive Models
  4. 2021Imitation by Predicting Observations
  5. 2023A Strong Baseline for Batch Imitation Learning
  6. 2019State Alignment-based Imitation Learning
  7. 2020State-only Imitation with Transition Dynamics Mismatch
  8. 2023Selective Sampling and Imitation Learning via Online Regression