Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 42

0% of course complete

42Stochastic and Semi-gradient Methods for Value Prediction

Module 0 · Stochastic Gradient Descent for Value Prediction

ARTICLEHow Gradient Descent Learns an Approximate Value Function

Reinforcement LearningStochastic and Semi-gradient Methods for Value Prediction

ARTICLE

How Gradient Descent Learns an Approximate Value Function

Loading lesson…

← PREVIOUSHistorical Development of Function Approximation Methods

NEXT →How Stochastic Gradient Descent Adjusts Value-Prediction Weights

LESSON PROGRESS

In progress

0%

NEXT LESSON

How Stochastic Gradient Descent Adjusts Value-Prediction Weights›