Artificial Intelligence: Reinforcement Learning in Python (Udemy.com)

Extensive, well balanced, straight to the point content on the topic of reinforcement learning, taught in a very clear way. It could do without the slightly arrogant tone at times, but other than that, it is excellent.

This is a great course with a lot of information. I really like that the instructor reviews the code in each series, and he offers a lot of code to review. It also exposed me to a lot of the math behind RL, which I appreciated. Better yet, the instructor highlights those formulas in the code. Still, this was a tough course to complete. I spent a lot of time outside the course reviewing the material to help me understand a lot of the nuance that gets passed over in the material. It could also benefit from more repetition; there are a lot of statements like "I will skip this because we covered it earlier" (15 to 20 hours ago). I'm not blessed with an exceptional memory so that usually forced me to stop progressing and go look it up. That would not be terrible if the comment included a general marker for where to go look, like go look in lesson 15.

This course allowed me to learn all the basic theory that is behind RL which is what I was looking for. Additionally, simple code scripts enabled myself to understand better what in the theory section was just words and concepts. Of course these topics require quite a good knowledge about maths which is, in this course, covered for everything is needed in order not to get lost.

This one is one of the best courses I've done in a long time. Even though is a high level course where you need not only good programming skills but also good probability knowledge. I suggest everyone to take the course along with any reinforcement learning book to make it easier.

This is a great introduction to reinforcement learning. There are many moments you have to think a little bit yourself, but not too much to get frustrated, just optimal. All code examples are very clearly written and explained.

One of the best courses I've ever taken on the topic. Super useful to learn building basic environments and RL agent dynamics, and to develop intuitions for more sophisticated models. The mathematical rigor comes together with a nice teaching strategy for the coding part.

Honestly, the best $29 I've ever spent. I used this to understand RL for my final data science master's project. While I love math, I struggle with it, primarily because I get hung up on notation ambiguities and variance between authors. However, this instructor didn't leave me hanging once. All math was thoroughly explained, ambiguities clarified, and they even highlight details that could easily be a sticking points for students. For me, there is nothing worse than books/courses that explain a key fundamental, and then say "I leave it as an exercise for the student to complete (or implement, or derive)", when the solution/implementation/derivation is not clear at all. I pay for learning materials to learn quickly, so this waste of time incenses me to no end. In this course, I only noticed one minor example of this and it was for a very obvious implementation, so was not a problem. I ignored all of the "fill in the blank code" assignments as this was not useful for my learning style, and I jumped directly to the full code implementations (tracing the code first, then watching the videos to clarify any sticking points). If you follow these videos in order, and run through the code, you will have a solid foundation in RL. Much thanks and praise to the instructor!!!

O material tem boa didática, ainda mais considerando que o assunto não é trivial. Ele dá vários exemplos de código que são muito úteis para entender o assunto na prática. Depois que fiz o curso pela primeira vez, vi que foram feitos ajustes que resolveram algumas críticas que eu tinha e, por isso, aumentei a nota que dei inicialmente. Alguém ainda pode achar que o curso demora um pouco a chegar nos algoritmos mais relevantes, mas isso porque ele se preocupa em dar uma boa base teórica (e acho isso positivo). Ele também não vai muito longe no assunto (ele não chega a apresentar os algoritmos mais modernos), deixando o curso um tanto incompleto. O mesmo instrutor/equipe tem dois outros cursos complementares sobre o assunto (o "Advanced Reinforcement Learning" é o melhor - 5 estrelas, para mim). Meu resumo é este: recomendo fortemente para quem quer uma *introdução* sólida no assunto de aprendizagem por reforço!

This is the kind of class that really help you build up a skill. It is simply brilliant. Theory is precise and concisely explicited including equations and exercices. The exercises are relevant and simple enough that all you have to care about is your understanding of the principles explained during the lectures. In addition, there are even tips and comments on how to use this class, how to use an online course, and how to build complete machine learning background. This is my first experience with Lazy Programmer Inc and even though, I did not follow other classes because they concern stuff that I already know, I would highly recommend them based on the content of this class and the quality of the teaching. I am even considering, going back to things I know just to revisit them in a pleasant, well-organised, concise way with a new take on it. Thanks you for the effort you put in your classes.

I loved the mix of theory and code, which allowed me to not only learn the theory, but actually implement it in code and check the result with the given solution. I could ask questions and get very fast responses. It really feels the instructor wants you to learn.

The explanations are very clear, and that It a good thing.

However the algorithm presentation is static, more interaction could have been perfect

Aún es prematuro pero de momento me está gustando mucho.