Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control

Abstract
Hierarchical Imitation Learning (HIL) has been proposed to recover highly-complex behaviors in long-horizon tasks from expert demonstrations by modeling the task hierarchy with the option framework. Existing methods either overlook the causal relationship between the subtask and its corresponding policy or cannot learn the policy in an end-to-end fashion, which leads to suboptimality. In this work, we develop a novel HIL algorithm based on Adversarial Inverse Reinforcement Learning and adapt it with the Expectation-Maximization algorithm in order to directly recover a hierarchical policy from the unannotated demonstrations. Further, we introduce a directed information term to the objective function to enhance the causality and propose a Variational Autoencoder framework for learning with our objectives in an end-to-end fashion. Theoretical justifications and evaluations on challenging robotic control tasks are provided to show the superiority of our algorithm.

Citation
Chen, J., Lan, T., & Aggarwal, V. (2023). Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control. 2023 IEEE International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra48891.2023.10160374

Publisher
IEEE

Conference/Event Name
2023 IEEE International Conference on Robotics and Automation (ICRA)

DOI
10.1109/icra48891.2023.10160374

arXiv
2210.01969

Additional Links
https://ieeexplore.ieee.org/document/10160374/

Relations
Is Supplemented By:
  • [Software]
    Title: LucasCJYSDL/HierAIRL: Codes of the paper: Hierarchical Adversarial Inverse Reinforcement Learning.. Publication Date: 2022-09-13. github: LucasCJYSDL/HierAIRL Handle: 10754/686459

Permanent link to this record

Version History

Now showing 1 - 2 of 2
VersionDateSummary
2*
2023-07-06 07:16:41
Published as conference paper
2022-10-10 11:18:48
* Selected version