Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch

Luca Viano, Yu-Ting Huang, Parameswaran Kamalaruban, Adrian Weller, Volkan Cevher

Keywords: Inverse Reinforcement Learning, Imitation Learning, Robust Reinforcement Learning

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.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: This paper studies the inverse reinforcement learning problem under a transition dynamics mismatch between the expert and the learner.

Code: https://github.com/lviano/RobustMCE_IRL/tree/master/robustIRLcode

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2007.01174/code)