WPO derives a closed-form policy update from Wasserstein gradient flows, which for Gaussian policies coincides with the standard policy gradient in expectation but with lower variance, and works for arbitrary stochastic policies without reparameterization.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Wasserstein Policy Optimization
WPO derives a closed-form policy update from Wasserstein gradient flows, which for Gaussian policies coincides with the standard policy gradient in expectation but with lower variance, and works for arbitrary stochastic policies without reparameterization.