A practical algorithm quantifies potential missing observations in IRL by computing minimal perturbations to recorded data that render expert actions optimal.
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Quantifying Potential Observation Missingness in Inverse Reinforcement Learning
A practical algorithm quantifies potential missing observations in IRL by computing minimal perturbations to recorded data that render expert actions optimal.