Robust Inverse Reinforcement Learning Under Transition Dynamics Mismatch

Abstract

We study the inverse reinforcement learning (IRL) problem under a transition dynamics mismatch between the expert and the learner. Specifically, we consider the Maximum Causal Entropy (MCE) IRL learner model and provide a tight upper bound on the learner's performance degradation based on the $\ell_1$-distance between the transition dynamics of the expert and the learner. Leveraging insights from the Robust RL literature, we propose a robust MCE IRL algorithm, which is a principled approach to help with this mismatch. Finally, we empirically demonstrate the stable performance of our algorithm compared to the standard MCE IRL algorithm under transition dynamics mismatches in both finite and continuous MDP problems.

PDF NeurIPS OpenReview Code Semantic Scholar

Cite

Text

Viano et al. "Robust Inverse Reinforcement Learning Under Transition Dynamics Mismatch." Neural Information Processing Systems, 2021.

Markdown

[Viano et al. "Robust Inverse Reinforcement Learning Under Transition Dynamics Mismatch." Neural Information Processing Systems, 2021.](https://mlanthology.org/neurips/2021/viano2021neurips-robust/)

BibTeX

@inproceedings{viano2021neurips-robust,
  title     = {{Robust Inverse Reinforcement Learning Under Transition Dynamics Mismatch}},
  author    = {Viano, Luca and Huang, Yu-Ting and Kamalaruban, Parameswaran and Weller, Adrian and Cevher, Volkan},
  booktitle = {Neural Information Processing Systems},
  year      = {2021},
  url       = {https://mlanthology.org/neurips/2021/viano2021neurips-robust/}
}