Courses Concepts Explore Playground Practice

← Back to course Reinforcement Learning

You are in chapter 55

0% of course complete

55Policy Parameterization for Continuous Actions

Module 0 · Representing Policies for Continuous Actions

ARTICLEParameterizing Policies with a Normal Distribution

Reinforcement LearningPolicy Parameterization for Continuous Actions

ARTICLE

Parameterizing Policies with a Normal Distribution

Loading lesson…

← PREVIOUSUsing a Normal Distribution for Continuous Actions

NEXT →How a Bernoulli-Logistic Unit Chooses Between Two Actions

LESSON PROGRESS

In progress

0%

NEXT LESSON

How a Bernoulli-Logistic Unit Chooses Between Two Actions›