Action-Constrained Imitation Learning

Chia-Han Yeh, Tse-Sheng Nan, Risto Vuorio, Shao-Hua Sun, Ping-Chun Hsieh

Keywords: action-constrained reinforcement learning, imitation learning, safety

TL;DR: We study a new problem setting termed Action-Constrained Imitation Learning and propose a method to mitigate the mismatch of occupancy measures between the expert and the learner caused by the action constraints.

Abstract:

Policy learning under action constraints plays a central role in ensuring safe behaviors in various robot control and resource allocation applications.
In this paper, we study a new problem setting termed Action-Constrained Imitation Learning (ACIL), where an action-constrained imitator aims to learn from a demonstrative expert with larger action space.
The fundamental challenge of ACIL lies in the unavoidable mismatch of occupancy measure between the expert and the imitator caused by the action constraints. We tackle this mismatch through $\textit{trajectory alignment}$ and propose DTWIL, which replaces the original expert demonstrations with a surrogate dataset that follows similar state trajectories while adhering to the action constraints. Specifically, we recast trajectory alignment as a planning problem and solve it via Model Predictive Control, which aligns the surrogate trajectories with the expert trajectories based on the Dynamic Time Warping (DTW) distance. Through extensive experiments, we demonstrate that learning from the dataset generated by DTWIL significantly enhances performance across multiple robot control tasks and outperforms various benchmark imitation learning algorithms in terms of sample efficiency.

Primary Area: reinforcement learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 14186