conftrace_

likelihood ratio method

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

optimal estimator (1) cubic regularization (1) policy newton (1) second-order stationary point (1) variational learning (1) gradient estimator (1) likelihood ratio (1) variance reduction (1) value function (1) sample complexity (1)

Papers

A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning AISTATS 2024 Evaluating the Variance of Likelihood-Ratio Gradient Estimators ICML 2017