Continuous-Time Policy Gradient from Discrete Data: Convergence Analysis and Model-Free Algorithms

Paper recorded by Signals 4 on 2026-10-20 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-20 on arXiv · recorded by Signals 4 on 2026-10-21

Category: cs.LG · 机器学习 · first seen 2026-10-21

Abstract

Continuous-time reinforcement learning seeks an optimal policy under unknown dynamics driven by stochastic differential equations using observations collected at discrete times. We develop a policy gradient framework that combines rigorous convergence analysis with learning from discrete data. We first establish a performance difference lemma and derive policy gradient formulas for randomized and

Read on arXiv →