Online inverse reinforcement learning with limited data
Abstract
This paper addresses the problem of online inverse reinforcement learning for systems with limited data and uncertain dynamics. In the developed approach, the state and control trajectories are recorded online by observing an agent perform a task, and reward function estimation is performed in real-time using a novel inverse reinforcement learning approach. Parameter estimation is performed concurrently to help compensate for uncertainties in the agent's dynamics. Data insufficiency is resolved by developing a data-driven update law to estimate the optimal feedback controller. The estimated controller can then be queried to artificially create additional data to drive reward function estimation.
Cite
@article{arxiv.2008.08972,
title = {Online inverse reinforcement learning with limited data},
author = {Ryan Self and S M Nahid Mahmud and Katrine Hareland and Rushikesh Kamalapurkar},
journal= {arXiv preprint arXiv:2008.08972},
year = {2020}
}
Comments
8 pages, 5 figures. arXiv admin note: text overlap with arXiv:2003.03912