Introduces a geometry-based framework for comparison-oracle optimization, with O(d log(d/ε)) comparisons for normal direction estimation and Õ(d D²/ε²) comparisons to reach ε level-set optimality gap under regularity, convexity, and growth conditions.
Preference-based rein- forcement learning: A formal framework and a policy iteration algorithm.Machine Learning, 89(1– 2):123–156
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Function-free Optimization via Comparison Oracles
Introduces a geometry-based framework for comparison-oracle optimization, with O(d log(d/ε)) comparisons for normal direction estimation and Õ(d D²/ε²) comparisons to reach ε level-set optimality gap under regularity, convexity, and growth conditions.