Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
Sebastian Tschiatschek, Ahana Ghosh, Luis Haug, Rati Devidze, Adish Singla
Abstract
Inverse reinforcement learning (IRL) enables an agent to learn complex behavior by observing demonstrations from a (near-)optimal policy. The typical assumption is that the learner's goal is to match the teacher’s demonstrated behavior. In this paper, we consider the setting where the learner has its own preferences that it additionally takes into consideration. These preferences can for example capture behavioral biases, mismatched worldviews, or physical constraints. We study two teaching approaches: learner-agnostic teaching, where the teacher provides demonstrations from an optimal policy ignoring the learner's preferences, and learner-aware teaching, where the teacher accounts for the learner’s preferences. We design learner-aware teaching algorithms and show that significant performance improvements can be achieved over learner-agnostic teaching.
BibTeX
@inproceedings{NEURIPS2019_3de568f8,
author = {Tschiatschek, Sebastian and Ghosh, Ahana and Haug, Luis and Devidze, Rati and Singla, Adish},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/3de568f8597b94bda53149c7d7f5958c-Paper.pdf},
volume = {32},
year = {2019}
}