Latest Courses
Business Analytics: Use Data Analysis for Financial IndustryCheck course
Akka Streams with Scala | Rock the JVMCheck course
Android app development course from Beginner to ProfessionalCheck course
Akka Serialization with Scala | Rock the JVMCheck course
Akka Remoting and Clustering with Scala | Rock the JVMCheck course
Learn C++ from scratchCheck course
Learn Dart & Flutter for Native Mobile Apps DevelopmentCheck course
Java Multithreading & Concurrency - Interview Practice ExamsCheck course
Programming Bootcamp for Kids and BeginnersCheck course
java EE : Practice Tests for Java EE CertificationCheck course
Business Analytics: Use Data Analysis for Financial IndustryCheck course
Akka Streams with Scala | Rock the JVMCheck course
Android app development course from Beginner to ProfessionalCheck course
Akka Serialization with Scala | Rock the JVMCheck course
Akka Remoting and Clustering with Scala | Rock the JVMCheck course
- 63% Artificial Intelligence: Reinforcement Learning in Python

Artificial Intelligence: Reinforcement Learning in Python

$29.99 $10.99Track price

Add your review
Add to wishlistAdded to wishlistRemoved from wishlist 0
Add to compare
8.5/10 (Our Score)
Product is rated as #47 in category Artificial Intelligence

When people talk about artificial intelligence, they usually don t mean supervised and unsupervised machine learning.

These tasks are pretty trivial compared to what we think of AIs doing – playing chess and Go, driving cars, and beating video games at a superhuman level.

Reinforcement learning has recently become popular for doing all of that and more.

Much like deep learning, a lot of the theory was discovered in the 70s and 80s but it hasn t been until recently that we ve been able to observe first hand the amazing results that are possible.

In 2016 we saw Google s AlphaGo beat the world Champion in Go.

We saw AIs playing video games like Doom and Super Mario.

Self–driving cars have started driving on real roads with other drivers and even carrying passengers (Uber), all without human assistance.

If that sounds amazing, brace yourself for the future because the law of accelerating returns dictates that this progress is only going to continue to increase exponentially.

Learning about supervised and unsupervised machine learning is no small feat. To date I have over SIXTEEN (16!) courses just on those topics alone.

And yet reinforcement learning opens up a whole new world. As you ll learn in this course, the reinforcement learning paradigm is more different from supervised and unsupervised learning than they are from each other.

Instructor Details

Today, I spend most of my time as an artificial intelligence and machine learning engineer with a focus on deep learning, although I have also been known as a data scientist, big data engineer, and full stack software engineer. I received my masters degree in computer engineering with a specialization in machine learning and pattern recognition. Experience includes online advertising and digital media as both a data scientist (optimizing click and conversion rates) and big data engineer (building data processing pipelines). Some big data technologies I frequently use are Hadoop, Pig, Hive, MapReduce, and Spark. I've created deep learning models to predict click-through rate and user behavior, as well as for image and signal processing and modeling text. My work in recommendation systems has applied Reinforcement Learning and Collaborative Filtering, and we validated the results using A/B testing. I have taught undergraduate and graduate students in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics for students attending universities such as Columbia University, NYU, Hunter College, and The New School. Multiple businesses have benefitted from my web programming expertise. I do all the backend (server), frontend (HTML/JS/CSS), and operations/deployment work. Some of the technologies I've used are: Python, Ruby/Rails, PHP, Bootstrap, jQuery (Javascript), Backbone, and Angular. For storage/databases I've used MySQL, Postgres, Redis, MongoDB, and more.

Specification: Artificial Intelligence: Reinforcement Learning in Python

Duration

12.5 hours

Year

2020

Level

Intermediate

Certificate

Yes

Quizzes

No

9 reviews for Artificial Intelligence: Reinforcement Learning in Python

3.6 out of 5
3
1
2
3
0
Write a review
Show all Most Helpful Highest Rating Lowest Rating
  1. Avatar

    Havana Diogo Alves Andrade

    Bom.

    Helpful(0) Unhelpful(0)You have already voted this
  2. Avatar

    Mayank M

    nice class

    Helpful(0) Unhelpful(0)You have already voted this
  3. Avatar

    Niels Pichon

    The name of the guy is well chosen: Everywhere where he can be lazy he is. And I am not talking about cheap tricks that work, I am talking about dodgy math explanations that skip most important steps, pseudo code that actually isn’t pseudo code, not rewriting the code to make changes (and faking the right behaviour instead) because it is too much work… So disappointed.

    Helpful(0) Unhelpful(0)You have already voted this
  4. Avatar

    Phumudzo Vusani Neluheni

    I’m glad for the experience as I’m now very familiar with Reinforcement Learning

    Helpful(0) Unhelpful(0)You have already voted this
  5. Avatar

    Andreas Zinonos

    This will be a long review, so I’ll provide a TL;DR version at the end. I’ve watched around 50% of this course so I feel like I have enough information to give a rating. I deduct 2 points for two reasons which I will go into detail below: a) The presentation and content ( 1) b) The author’s attitude and unhelpfulness ( 1 but could easily bump it to 2) Before the author gives me his default response Please see the prerequisites listed twice in the course description or Please watch the how to succeed in this course section, I need to mention that I have a BSc in Computer Science (with First Class) and an MSc in Artificial Intelligence (with Distinction) from two of the top UK universities. The reason I’m taking this course is that I had a not so well explained RL course at university, and since I was interested in the subject I wanted to learn it properly in more depth. Before I begin listing the negatives (which I’ll go into more detail) let me address the positives first: + The content is there, it does go into most things needed to learn and understand Reinforcement Learning + There’s code examples and provided code which is very useful + The course is nicely structured Now for the negatives: a) Presentation and content: The content is there, but the presentation and slides are stale some times. I know this is a maths heavy course but it wouldn’t hurt to have more lively slides with more examples or perhaps figures (even though the author has responded to this previously saying he doesn’t want to make it an action film, which is a weird response that dodges the addressed issue). The talking is a bit monotonic, speeding the video doesn’t always help as the author is sometimes already going fast over the material. The author doesn’t explain the maths properly, he rushes over it. True, you do have to write it down and try to do the calculations yourself and it does help a lot, but he could be more helpful by going into a bit more detail. It doesn’t have to be beginner level calculus, but at least explaining some concepts briefly would help. Another great idea is that the math parts could be written down on a blackboard (similarly to KhanAcademy) instead of just having the equations on slides, so that you can see his workings. Instead, he just tells you to do it yourself as an exercise. You could ask a question you say? Well I’ll address this in a bit. Just to be clear I did take the time to write down and understand the math, but I would expect more help from the author in doing this. In my opinion, the best way to explain code is to have a video where you are writing the code in real time and explaining your thought process. In this course, the code is already given and the author simply goes over the functions and tells you what they do. Though better than nothing, the way I proposed has been much more effective for me. Of course you should still try and code everything yourself to understand the solution. b) The author s attitude and unhelpfulness: The author is clearly arrogant, has a horrible attitude towards the students and is very unhelpful whenever someone asks a question. If you don t believe me, go and read his responses to a lot of the questions in the courses or even the reviews. His attitude is always I know everything, I am right, and if you didn t understand something it s your fault . If you lack any small form of understanding, he will tell you that you are missing the pre requisites and you should buy his other courses. No man, if I have a small lack of understanding which could be solved by you explaining something for 2 minutes more I don t have to buy another one of your courses to find the small piece of information I m missing, which could be 1% of that course. It s the teacher s job to help the student. When asked a question, he rarely responds to the question directly. The responses are usually in the form of Well just try it yourself and find out or Why do you think that is? or It s simple, I can t see what exactly you don t understand? . In the few cases where he actually does answer the question, he really makes sure that he doesn t give the answer easily but makes it a pain. Throughout my whole academic life, I really hated these types of teachers. If someone is asking you a question, you should just answer the damn question! I know I can try it myself, ask other people, do research, write code or whatever else. The reason I m asking you is because I have either tried those things and I couldn t find a solution, or it would simply take too much time to do that every time and you could simply answer the question to save me all that hassle. You might think that this would take away from the learning, but this is a senseless argument. There are many cases where the difference in how well you understand a solution by being given the answer or finding it on your own is so small that it s just not worth the time to do the latter. To me this communicates one of two things: i) The author does not understand the material well enough to give a good explanation to a question, or ii) He doesn t really care to spend time helping a student. The author never accepts criticism. In the reviews he s got (and I ve read many before writing this), he has not once accepted any form of criticism as a form of him having a subpar course or him having any blame. His attitude is that Lazy Programmer has created a perfect course, and all the people who have any criticisms are wrong, had wrong expectations, lacked the prerequisites, or are the wrong target market. This makes the author even more unappealing to me. By not knowing how to take criticism, you will never improve your courses but you will protect your inflated ego. I have seen many good points by other fellow students which you simply ignored or turned against the student instead of taking a moment to think about it. This is just disappointing. Unfortunately, there are not many other decent Reinforcement Learning courses I ve found so if you want to learn this stuff, you might have to stick with this one. And again, the course does teach you a lot if you are willing to put the work in, stop for a bit and learn some things on your own in the cases of the quick and not so well explained math parts and ignore the author s behavior, probably by avoiding asking questions. Obviously, even though the course is not perfect my main issue is with the author and not the course. Had he been a more open minded individual with less of an ego, listened to the reviews and gave good answers to questions, this course could have been transformed to a much higher quality one. I ve spent a lot of time to write this review, so I hope you, Lazy Programmer, will for once take this into consideration and change your attitude. Thanks for making this course anyway, it has been useful. If you need any feedback on how you could improve your course, feel free to PM me. TL;DR The course and content is ok, the presentation could be better though. The stuff you need to learn is there, but you have to put a bit more effort occasionally since the author doesn t always explain things in detail. A bigger issue than the actual course is the author s bad attitude towards the student. Do not expect to get a proper answer if you ask a question. Had this not been the case, the course could have been a more enjoyable experience.

    Helpful(0) Unhelpful(0)You have already voted this
  6. Avatar

    Henry Stewart

    not very well explained. made learning slower than it should have been. could have made it much easier to follow

    Helpful(0) Unhelpful(0)You have already voted this
  7. Avatar

    Musab Faiyazuddin

    I think it includes too much text in the slides, a bit hard to read.

    Helpful(0) Unhelpful(0)You have already voted this
  8. Avatar

    Christian Lopez

    It has been very interesting, also have resources good enough for my self knownledge. Some issues with some code, but that’s natural. Great course!

    Helpful(0) Unhelpful(0)You have already voted this
  9. Avatar

    Monil Modi

    Concept is understandable but coding is a bit difficult to understand

    Helpful(0) Unhelpful(0)You have already voted this

    Add a review

    Your email address will not be published. Required fields are marked *

    This site uses Akismet to reduce spam. Learn how your comment data is processed.

    Artificial Intelligence: Reinforcement Learning in Python
    Artificial Intelligence: Reinforcement Learning in Python

    $29.99 $10.99

    Price tracking

    Java Code Geeks
    Logo
    Register New Account
    Reset Password
    Compare items
    • Total (0)
    Compare
    Shopping cart