About this document
Stochastic Approximation & Gradient Descent by liang is a document available to read on EtoBox.
This lecture introduces stochastic approximation and stochastic gradient descent, focusing on bridging the knowledge gap between Monte Carlo learning and temporal-difference learning. It covers the Robbins-Monro algorithm, which is foundational in stochastic approximation, and discusses its application in mean estimation. The lecture outlines the convergence properties of these algorithms and emphasizes their importance in reinforcement learning.
- Author
- liang
- Language
- EN