TY - JOUR
T1 - Showing versus doing
T2 - 30th Annual Conference on Neural Information Processing Systems, NIPS 2016
AU - Ho, Mark K.
AU - Littman, Michael L.
AU - MacGlashan, James
AU - Cushman, Fiery
AU - Austerweil, Joseph L.
N1 - Publisher Copyright:
© 2016 NIPS Foundation - All Rights Reserved.
PY - 2016
Y1 - 2016
N2 - People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contrast, teaching by demonstration has been less well studied computationally. Here, we develop a Bayesian model for teaching by demonstration. Stark differences arise when demonstrators are intentionally teaching (i.e. showing) a task versus simply performing (i.e. doing) a task. In two experiments, we show that human participants modify their teaching behavior consistent with the predictions of our model. Further, we show that even standard IRL algorithms benefit when learning from showing versus doing.
AB - People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contrast, teaching by demonstration has been less well studied computationally. Here, we develop a Bayesian model for teaching by demonstration. Stark differences arise when demonstrators are intentionally teaching (i.e. showing) a task versus simply performing (i.e. doing) a task. In two experiments, we show that human participants modify their teaching behavior consistent with the predictions of our model. Further, we show that even standard IRL algorithms benefit when learning from showing versus doing.
UR - http://www.scopus.com/inward/record.url?scp=85018924601&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85018924601&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85018924601
SN - 1049-5258
SP - 3035
EP - 3043
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
Y2 - 5 December 2016 through 10 December 2016
ER -