Dynamic Programming | Free Reinforcement Learning Course Module 4

preview_player
Показать описание
In module 4 we're going to cover some of the basic theory of dynamic programming. This is a model based class of algorithms for solving reinforcement learning problems, by iteratively solving the Bellman equation.

We'll cover policy evaluation, policy improvement, and value iteration as solutions to the Bellman equation.

We also have our first homework assignment, for which I'll provide the solution in module 5.

#reinforcementlearning #artificialintelligence #dynamicprogramming

Learn how to turn deep reinforcement learning papers into code:

Get instant access to all my courses, including the new Prioritized Experience Replay course, with my subscription service. $29 a month gives you instant access to 42 hours of instructional content plus access to future updates, added monthly.

Or, pickup my Udemy courses here:

Deep Q Learning:

Actor Critic Methods:

Curiosity Driven Deep Reinforcement Learning

Natural Language Processing from First Principles:
Reinforcement Learning Fundamentals

Here are some books / courses I recommend (affiliate links):

Come hang out on Discord here:

Background music is "Airglow" by Stellardrone. You can download it here
Рекомендации по теме
Комментарии
Автор

This content is sponsored by my Udemy courses. Level up your skills by learning to turn papers into code. See the links in the description.

As promised here are the time stamps for the algorithms for your assignment.
Policy Evaluation 02:47
Policy Iteration 03:58
Value Iteration 04:45

MachineLearningwithPhil
Автор

Nice video!! When to use value iteration and when policy iteration? What are the advantages and disadvantages?

stefanherbek
join shbcf.ru