MUSEL selects training samples by multiplying model uncertainty, distance to known inputs, and learning progress, improving sample efficiency for simulated robot effect prediction.
Journal of Artificial Intelligence Research75, 709–745 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sample Efficient Robot Learning in Supervised Effect Prediction Tasks
MUSEL selects training samples by multiplying model uncertainty, distance to known inputs, and learning progress, improving sample efficiency for simulated robot effect prediction.