Milo Spencer-Harper
This course is designed for beginners to machine learning. Some of the most exciting advances in artificial intelligence have occurred by challenging neural networks to play games. I will introduce the concept of reinforcement learning, by teaching you to code a neural network in Python capable of delayed gratification.
We will use the NChain game provided by the Open AI institute. The computer gets a small reward if it goes backwards, but if it learns to make short term sacrifices by persistently pressing forwards it can earn a much larger reward. Using this example I will teach you Deep Q Learning – a revolutionary technique invented by Google DeepMind to teach neural networks to play chess, Go and Atari.
Instructor Details
Courses : 2
Specification: Machine Learning: Beginner Reinforcement Learning in Python
|
15 reviews for Machine Learning: Beginner Reinforcement Learning in Python
Add a review
| Price | $9.99 |
|---|---|
| Provider | |
| Duration | 2 hours |
| Year | 2020 |
| Level | Beginner |
| Language | English |
| Certificate | Yes |
| Quizzes | Yes |
$9.99
Ed Moyse –
Excellent course that’s completely practical too!
Leanne Ronk –
Similar to Milo’s other course on machine learning, this course is also incredibly accessible. Milo has a great gift for explaining and simplifying complex concepts. I find machine learning really interesting, and I love that Milo makes it possible to grasp the basics of reinforcement learning without having to be a maths or programming expert. Thanks so much Milo! I would highly recommend!
Louise Croft –
I’ve been meaning to look into Machine Learning for ages because it’s so powerful and I’m glad I finally made the step. This course is really practical and explains everything in such a straight forward way. Quizzes were helpful too. Recommend!!
Erkki Muuga –
It was quite exciting to create this machine learning code, because with every chapter, we added more intelligence to the program. First, we created a program that takes steps and gets rewards. Secondly, we gave it memory of the rewards it got. Third, we taught it to analyse the reward memory. Finally, we taught the program to predict the future rewards based on its past experiences. By graphing the learning curve we could actually see how the program is learning to go for the higher reward as it plays. Milo took it even further by introducing Neural Networks instead of Q table. By graphing the results with both methods, we could see how Neural Networks is the superior one, as it learns faster. Regarding the coding videos, I recommend just watching them at first and try to understand the logic behind it. Then replay it and write the code. It makes this complex topic easier to comprehend. Overall a great course! The teacher explains rather complicated mathematical algorithms in a way I could understand.
Chilion Snoek –
An amazing course that teaches quickly but thoroughly techniques and the theory behind it. I’m very very happy with the new knowledge gained.
Srinjoy Roy –
Yes!
Paulo Jarbas Camur a –
Great course, congratulations. I would like see more courses like this and explore more complex games like chess or tetris.
Britt H Braswell –
Amazing beginning to my journey to just start doing something in AI! Thank you
Shahram Bahman Rokh –
Very good introductory course to Deep Reinforcement Learning. I liked the fact that the instructor did not over complicate it with going into details of mathematical equations and theory behind it. It gives a basic knowledge/theory for each segment (Q learning, Neural Network and DQN) and then shows you how to write the code. The coding might seem a bit confusing because of the pace of the course however the code can be learned and played with at your own pace. One thing that might be good to include in future is how to build your own environment and how to define your actions and rewards within that environment. Thank you very much.
Sai Raghava –
Really amazing work done here. Proper hands on experience in learning the concept. Would definitely recommend trying it out.
Craig Brennan –
Love this course. Very interesting.
Alexandre VASSILTCHENKO –
Best course on reinforcement learning i’ve seen so far.
Foster L Ming –
This is a good intro to AI
Ansh Sandhu –
Extremely high level introduction, not very useful.
Ab Faha –
clear, concise and covers the basics in 2 hours. I enjoyed it for sure!