Flexible Reward Plans to Elicit Truthful Predictions in Crowdsourcing.

Yuko Sakurai Satoshi Oyama Masato Shinoda Makoto Yokoo

Published in: HCOMP (2015)

Keyphrases

reinforcement learning
plan generation
lightweight
real time
case study
mobile robot
long run
partially ordered
data mining
multi agent
bandit problems
amazon mechanical turk
highly dynamic environments