Bisimulator uses bisimulation metrics to modify rewards and observations, letting unconstrained RL policies approximately satisfy demographic parity in lending and college admissions benchmarks.
My fair bandit: Distributed learning of max-min fairness with multi-player bandits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fairness in Reinforcement Learning with Bisimulation Metrics
Bisimulator uses bisimulation metrics to modify rewards and observations, letting unconstrained RL policies approximately satisfy demographic parity in lending and college admissions benchmarks.