Fake It Till You Make It: Learning-Compatible Performance Support

Jonathan Bragg, Emma Brunskill
Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, PMLR 115:915-924, 2020.

Abstract

A longstanding goal of artificial intelligence is to develop technologies that augment or assist humans. Current approaches to developing agents that can assist humans focus on adapting behavior of the assistant, and do not consider the potential for assistants to support human learning. We argue that in many cases it is worthwhile to provide assistance in a manner that also promotes task learning or skill maintenance. We term such assistance Learning-Compatible Performance Support, and present the Stochastic Q Bumpers algorithm for greatly improving learning outcomes while still providing high levels of performance support. We demonstrate the effectiveness of our approach in multiple domains, including a complex flight control task.

Cite this Paper

BibTeX
@InProceedings{pmlr-v115-bragg20a, title = {Fake It Till You Make It: Learning-Compatible Performance Support}, author = {Bragg, Jonathan and Brunskill, Emma}, booktitle = {Proceedings of The 35th Uncertainty in Artificial Intelligence Conference}, pages = {915--924}, year = {2020}, editor = {Adams, Ryan P. and Gogate, Vibhav}, volume = {115}, series = {Proceedings of Machine Learning Research}, month = {22--25 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v115/bragg20a/bragg20a.pdf}, url = {https://proceedings.mlr.press/v115/bragg20a.html}, abstract = {A longstanding goal of artificial intelligence is to develop technologies that augment or assist humans. Current approaches to developing agents that can assist humans focus on adapting behavior of the assistant, and do not consider the potential for assistants to support human learning. We argue that in many cases it is worthwhile to provide assistance in a manner that also promotes task learning or skill maintenance. We term such assistance Learning-Compatible Performance Support, and present the Stochastic Q Bumpers algorithm for greatly improving learning outcomes while still providing high levels of performance support. We demonstrate the effectiveness of our approach in multiple domains, including a complex flight control task.} }
Endnote
%0 Conference Paper %T Fake It Till You Make It: Learning-Compatible Performance Support %A Jonathan Bragg %A Emma Brunskill %B Proceedings of The 35th Uncertainty in Artificial Intelligence Conference %C Proceedings of Machine Learning Research %D 2020 %E Ryan P. Adams %E Vibhav Gogate %F pmlr-v115-bragg20a %I PMLR %P 915--924 %U https://proceedings.mlr.press/v115/bragg20a.html %V 115 %X A longstanding goal of artificial intelligence is to develop technologies that augment or assist humans. Current approaches to developing agents that can assist humans focus on adapting behavior of the assistant, and do not consider the potential for assistants to support human learning. We argue that in many cases it is worthwhile to provide assistance in a manner that also promotes task learning or skill maintenance. We term such assistance Learning-Compatible Performance Support, and present the Stochastic Q Bumpers algorithm for greatly improving learning outcomes while still providing high levels of performance support. We demonstrate the effectiveness of our approach in multiple domains, including a complex flight control task.
APA
Bragg, J. & Brunskill, E.. (2020). Fake It Till You Make It: Learning-Compatible Performance Support. Proceedings of The 35th Uncertainty in Artificial Intelligence Conference, in Proceedings of Machine Learning Research 115:915-924 Available from https://proceedings.mlr.press/v115/bragg20a.html.

Related Material