Practical Bayesian Inverse Reinforcement Learning for Robot Navigation
Abstract
Inverse reinforcement learning (irl) provides a concise framework for learning behaviors from human demonstrations; and is highly desired in practical and difficult to specify tasks such as normative robot navigation. However, most existing irl algorithms are often ladened with practical challenges such as representation mismatch and poor scalability when deployed in real world tasks. Moreover, standard reinforcement learning (rl) representations often do not allow for incorporation of task constraints common for example in robot navigation. In this paper, we present an approach that tackles these challenges in a unified manner and delivers a learning setup that is both practical and scalable. We develop a graph-based spare representation for rl and a scalable irl algorithm based on sampled trajectories. Experimental evaluation in simulation and from a real deployment in a busy airport demonstrate the strengths of the learning setup over existing approaches.
Cite
Text
Okal and Arras. "Practical Bayesian Inverse Reinforcement Learning for Robot Navigation." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2016. doi:10.1007/978-3-319-46131-1_33Markdown
[Okal and Arras. "Practical Bayesian Inverse Reinforcement Learning for Robot Navigation." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2016.](https://mlanthology.org/ecmlpkdd/2016/okal2016ecmlpkdd-practical/) doi:10.1007/978-3-319-46131-1_33BibTeX
@inproceedings{okal2016ecmlpkdd-practical,
title = {{Practical Bayesian Inverse Reinforcement Learning for Robot Navigation}},
author = {Okal, Billy and Arras, Kai Oliver},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2016},
pages = {271-274},
doi = {10.1007/978-3-319-46131-1_33},
url = {https://mlanthology.org/ecmlpkdd/2016/okal2016ecmlpkdd-practical/}
}