A quantile-based data preprocessing method, CFSMDM, makes offline reinforcement learning approximately counterfactually fair under non-additive noise, with bounded suboptimality and unfairness.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Distribution Mapping Approach to Counterfactually Fair Reinforcement Learning
A quantile-based data preprocessing method, CFSMDM, makes offline reinforcement learning approximately counterfactually fair under non-additive noise, with bounded suboptimality and unfairness.