An imitation learning method trains active learning agents to jointly optimize internal learning objectives and externally imposed environmental constraints, with experiments showing statistical outperformance on a concept learning task under most constrained conditions.
Transparent active learning for robots
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Active Learning within Constrained Environments through Imitation of an Expert Questioner
An imitation learning method trains active learning agents to jointly optimize internal learning objectives and externally imposed environmental constraints, with experiments showing statistical outperformance on a concept learning task under most constrained conditions.