Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees
Abstract
Inverse Reinforcement Learning (IRL) is the problem of finding a reward function which describes observed/known expert behavior. The IRL setting is remarkably useful for automated control, in situations where the reward function is difficult to specify manually or as a means to extract agent preference. In this work, we provide a new IRL algorithm for the continuous state space setting with unknown transition dynamics by modeling the system using a basis of orthonormal functions. Moreover, we provide a proof of correctness and formal guarantees on the sample and time complexity of our algorithm. Finally, we present synthetic experiments to corroborate our theoretical guarantees.
Cite
Text
Dexter et al. "Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees." Neural Information Processing Systems, 2021.Markdown
[Dexter et al. "Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees." Neural Information Processing Systems, 2021.](https://mlanthology.org/neurips/2021/dexter2021neurips-inverse/)BibTeX
@inproceedings{dexter2021neurips-inverse,
title = {{Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees}},
author = {Dexter, Gregory and Bello, Kevin and Honorio, Jean},
booktitle = {Neural Information Processing Systems},
year = {2021},
url = {https://mlanthology.org/neurips/2021/dexter2021neurips-inverse/}
}