Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 8

0% of course complete

8Gradient Bandit Algorithms for Action Selection

Module 0 · Introduction to Gradient Bandit Algorithms

ARTICLEHow Numerical Preferences Guide Action Selection

Reinforcement LearningGradient Bandit Algorithms for Action Selection

ARTICLE

How Numerical Preferences Guide Action Selection

Loading lesson…

← PREVIOUSWhere UCB Action Selection Becomes Difficult

NEXT →How Stochastic Gradient Ascent Adjusts Action Preferences

LESSON PROGRESS

In progress

0%

NEXT LESSON

How Stochastic Gradient Ascent Adjusts Action Preferences›