Pb-MORL learns a multi-objective reward model from preference comparisons and claims to achieve Pareto-optimal policies, outperforming an oracle in energy and highway tasks.
Active learning with fairness-aware clustering for fair classification considering multiple sensitive attributes,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Preference-based Multi-Objective Reinforcement Learning
Pb-MORL learns a multi-objective reward model from preference comparisons and claims to achieve Pareto-optimal policies, outperforming an oracle in energy and highway tasks.