Malliavin calculus reformulates counterfactual gradient estimation as ratios of unconditioned expectations to achieve standard convergence rates in adaptive IRL.
Nualart,The Malliavin calculus and related topics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Malliavin Calculus for Counterfactual Gradient Estimation in Adaptive Inverse Reinforcement Learning
Malliavin calculus reformulates counterfactual gradient estimation as ratios of unconditioned expectations to achieve standard convergence rates in adaptive IRL.