EIG-based query selection for full-trajectory demonstrations reduces the number of human demonstrations needed to learn a reward in tabular gridworlds compared to random and entropy-based baselines.
Human Compatible: Artificial Intelligence and the Problem of Control
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Toward Information Theoretic Active Inverse Reinforcement Learning
EIG-based query selection for full-trajectory demonstrations reduces the number of human demonstrations needed to learn a reward in tabular gridworlds compared to random and entropy-based baselines.