TY - JOUR
T1 - Expert Intervention Learning
T2 - An online framework for robot learning from explicit and implicit human feedback
AU - Spencer, Jonathan
AU - Choudhury, Sanjiban
AU - Barnes, Matthew
AU - Schmittle, Matthew
AU - Chiang, Mung
AU - Ramadge, Peter
AU - Srinivasa, Sidd
N1 - Funding Information:
This work was (partially) funded by the DARPA Dispersed Computing program, NIH R01 (R01EB019335), NSF CPS (#1544797), NSF NRI (#1637748), the Office of Naval Research, RCTA, Amazon, and Honda Research Institute USA.
Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2022/1
Y1 - 2022/1
N2 - Scalable robot learning from human-robot interaction is critical if robots are to solve a multitude of tasks in the real world. Current approaches to imitation learning suffer from one of two drawbacks. On the one hand, they rely solely on off-policy human demonstration, which in some cases leads to a mismatch in train-test distribution. On the other, they burden the human to label every state the learner visits, rendering it impractical in many applications. We argue that learning interactively from expert interventions enjoys the best of both worlds. Our key insight is that any amount of expert feedback, whether by intervention or non-intervention, provides information about the quality of the current state, the quality of the action, or both. We formalize this as a constraint on the learner’s value function, which we can efficiently learn using no regret, online learning techniques. We call our approach Expert Intervention Learning (EIL), and evaluate it on a real and simulated driving task with a human expert, where it learns collision avoidance from scratch with just a few hundred samples (about one minute) of expert control.
AB - Scalable robot learning from human-robot interaction is critical if robots are to solve a multitude of tasks in the real world. Current approaches to imitation learning suffer from one of two drawbacks. On the one hand, they rely solely on off-policy human demonstration, which in some cases leads to a mismatch in train-test distribution. On the other, they burden the human to label every state the learner visits, rendering it impractical in many applications. We argue that learning interactively from expert interventions enjoys the best of both worlds. Our key insight is that any amount of expert feedback, whether by intervention or non-intervention, provides information about the quality of the current state, the quality of the action, or both. We formalize this as a constraint on the learner’s value function, which we can efficiently learn using no regret, online learning techniques. We call our approach Expert Intervention Learning (EIL), and evaluate it on a real and simulated driving task with a human expert, where it learns collision avoidance from scratch with just a few hundred samples (about one minute) of expert control.
UR - http://www.scopus.com/inward/record.url?scp=85117255015&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85117255015&partnerID=8YFLogxK
U2 - 10.1007/s10514-021-10006-9
DO - 10.1007/s10514-021-10006-9
M3 - Article
AN - SCOPUS:85117255015
SN - 0929-5593
VL - 46
SP - 99
EP - 113
JO - Autonomous Robots
JF - Autonomous Robots
IS - 1
ER -